Abstract: A motion-aware keypoint selection system adaptable to iterative closest point (ICP) includes a pruning unit that receives an image and selects at least one region of interest (ROI) composed of a selected subset of points on the image; a point quality estimation unit that receives the ROI and generates point quality; and a suppression unit that receives the point quality and generates keypoints. In one embodiment, a near edge region (NER) is selected as the ROI. In another embodiment, the point quality estimation unit generates point quality according to point motion and point depth.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining an input including an image of a plant, identifying a species of the plant by use of visual recognition of the image. The image is analyzed for symptoms and candidate diagnoses are selected from a diagnostic repository according to the symptoms. With respective candidate diagnoses, a confidence score and a treatment regimen are associated. According to a treatment mode, the candidate diagnoses and treatment regimen are delivered.

Abstract: A system and processing methods for configuring and utilizing a convolutional neural network (CNN) for plant disease recognition are disclosed. In some embodiments, the system is programmed to collect photos of infected plants or leaves where regions showing symptoms of infecting diseases are marked. Each photo may have multiple marked regions. Depending on how the symptoms are sized or clustered, one marked region may include only one lesion caused by one disease, while another may include multiple, closely-spaced lesions caused by one disease. The system is programmed to determine anchor boxes having distinct aspect ratios from these marked regions for each convolutional layer of a single shot multibox detector (SSD). For certain types of plants, common diseases lead to relatively many aspect ratios, some having relatively extreme values. The system is programmed to then train the SSD using the marked regions and the anchor boxes and apply the SSD to new photos to identify diseased plants.

Abstract: The present technology relates an inspection apparatus, an inspection method and a program by which accurate measurement light correction can be performed. The inspection apparatus calculates a correction gain of a spectrum based on reference spectral information, under a reference light source, of a reference reflector plate having a characteristic according to an inspection object and measurement spectral information of the reference reflector plate obtained by sensing under a measurement light source, and corrects measurement spectral information of the inspection object obtained by the sensing under the measurement light source based on the calculated correction gain. The present technology can be applied, for example, to a vegetation inspection apparatus that measures a vegetation index of a normalized vegetation index (NDVI) or the like.

Abstract: Disclosed are devices, systems, apparatus, methods, products, and other implementations, including a method to detect pattern characteristics in target specimens that includes acquiring sensor data for the target specimens, dividing the acquired sensor data into a plurality of data segments, and generating, by multiple neural networks that each receives the plurality of data segments, multiple respective output matrices, with each data element of the multiple respective output matrices being representative of a probability that corresponding sensor data of a respective one of the plurality of data segments includes a pattern characteristic in the target specimens. The method further includes determining by another neural network, based on the multiple respective output matrices generated by the multiple neural networks, a presence of the pattern characteristic in the target specimens.

Abstract: Systems and methods for generating crop yield maps are provided, in one example embodiment, a method can include accessing, by one or more processors, data indicative of crop yield for a field area; and accessing, by the one or more processors, one or more data types associated with the field area. Each of the data types can provide a geospatial distribution of data associated with vegetation across the field area. The method can further include determining, by the one or more processors, a crop yield distribution for the field area based at least in part on the data indicative of crop yield and the one or more data types; and generating, by the one or more processors, a yield map for the field area based at least in part on the crop yield distribution.

Abstract: In some embodiments, the system is programmed to build from multiple training sets multiple digital models, each for recognizing plant diseases having symptoms of similar sizes. Each digital model can be implemented with a deep learning architecture that classifies an image into one of several classes. For each training set, the system is thus programmed to collect images showing symptoms of one or more plant diseases having similar sizes. These images are then assigned to multiple disease classes. For a first one of the training sets used to build the first digital model, the system is programmed to also include images that correspond to a healthy condition and images of symptoms having other sizes. These images are then assigned to a no-disease class and a catch-all class. Given a new image from a user device, the system is programmed to then first apply the first digital model.

Abstract: A magnetic resonance imaging apparatus according to an embodiment includes a display, an input interface, and processing circuitry. The display displays at least a locator image and a reference image. The input interface sets a region of interest on the locator image displayed on the display. The processing circuitry scans a subject to obtain three dimensional data, generates a locator image from the three dimensional data and displaying the locator image on the display, generates a reference image corresponding to the location of the region of interest and displaying the reference image on the display, and makes, when a size or position of the region of interest on one of the locator image and the reference image is changed by the input interface, adjustments to correspondingly change the display magnification or position of the other one of the locator image and the reference image.

Abstract: A plant growth measurement and prediction system uses drone-captured images to measure the current growth of particular plant species and/or to predict future growth of the plant species. For example, the system instructs a drone to fly along a flight path and capture images of the land below. The captured images may include both thermographic images and high-resolution images. The system processes the images to create an orthomosaic image of the land, where each pixel in the orthomosaic image is associated with a brightness temperature. The system then uses plant species to brightness temperature mappings and the orthomosaic image to identify current plant growth. The system generates a diagnostic model using the orthomosaic image to then predict future plant growth.

Abstract: An arrangement of physical objects can be analyzed using a captured digital image of the arrangement and a reference display file database. A processing device communicatively coupled to the reference display file database receives the captured image depicting the arrangement of physical objects and accesses a reference display file from the reference display file database. The reference display file includes multi-viewpoint image data and scoring components. The processing device identifies at least some of the physical objects using the reference display file. The processing device scores each identified object for such attributes as presence, position and orientation using the scoring components from the reference display file, producing an overall score based on the scoring of each identified object. The processing device can then transmit the overall score to other systems.

Abstract: A system and method is provided for generating textured building models from wirelessly captured ground-level imagery. Ground-level images of facades of building objects are collected for identification of geometry planes and generation of building façade geometry. The 3D building model is properly geo-positioned, scaled and textured.

Abstract: A game scoring camera system is disclosed for capturing images of game animals for the purpose of scoring the antlers using an accepted scoring method. One or more cameras are used in a multiscopic arrangement for capturing two-dimensional (2-D) images which are then converted to three-dimensional (3-D) data models, the resulting 3-D data models being used for determining measurements of various antler structures for calculating a score for the set of antlers captured in the images, the score being based on existing antler scoring systems. Some embodiments include one or more cameras, each being mounted on an unmanned aerial vehicle or drone, for capturing images during an aerial survey of game animals located within a particular area. Other embodiments include at least two cameras mounted in a stationary configuration for capturing images of game animals located within a particular area.

Abstract: A method and system for generating a map identifying the size and location of anomalous crop health patterns of a geographic area. Predictive crop health forecasting based historical crop health images generates expected crop health images. Statistical parametric mapping is used to model differences in the expected crop health images and current crop health images to generate a statistical parametric map. Regions of anomalous crop health based on the modeled differences are identified in the statistical parametric map. The number of the identified anomalous crop health regions and the size of each of the identified anomalous crop health regions are determined. The statistical significance of the size and number of the anomalous crop health regions relative to the expected crop health is quantified. A map of anomalous crop health patterns delineates the anomalous crop health regions and the statistical significance of the size and number of anomalous crop health regions.

Abstract: The present invention relates to a method of calculating a Topography Adjusted Vegetation Index (TAVI) based on a band ratio model and a solar altitude angle. The method includes the following steps: obtaining the apparent reflectance data of a remote sensing image through image preprocessing, analyzing the quality of the image and numerical distribution, calculating a Shadow Vegetation Index (SVI), and constructing a TAVI combinational algorithm: TAVI = B ir B r + f ? ( ? ) · 1 B r , calculating an adjustment factor f(?) with the solar altitude angle, and finally obtaining anti-topographic effect TAVI vegetation information. The TAVI in the present invention is composed of two band ratio submodels RVI and SVI, the denominators of both of which are red band data of a remote sensing image, and the adjustment factor f(?), which is calculated by a solar altitude angle as a parameter with a sensor factor applied, has great physical significance.

Abstract: In embodiments, acquiring sensor data associated with a plant growing in a field, and analyzing the sensor data to extract, while in the field, one or more phenotypic traits associated with the plant from the sensor data. Indexing, while in the field, the one or more phenotypic traits to one or both of an identifier of the plant or a virtual representation of a part of the plant, and determining one or more plant insights based on the one or more phenotypic traits, wherein the one or more plant insights includes information about one or more of a health, a yield, a planting, a growth, a harvest, a management, a performance, and a state of the plant. One or more of the health, yield, planting, growth, harvest, management, performance, and the state of the plant are included in a plant insights report that is generated.

Abstract: The disclosure relates to methods and related systems for precision crop modeling and management using the same. Precision crop modeling and management can be incorporated into various methods for growing plants such as crop plants and various methods for managing the growth of such plants in a particular field. The methods generally utilize in-season information relating to weather conditions actually experienced by the field to prepare mid-season, updated crop management plans. A crop management plan is determined using a crop model incorporating a variety of inputs and plant-specific material and energy balances to specify one or more grower-controlled management parameters. An updated plan for a given field can be followed by a grower to increase crop yield and/or optimize one or more other crop or field parameters.

Abstract: An image of a block or the like entering a space above a play mat is picked up by an image pickup apparatus, and an information processing apparatus detects and recognizes the block on the basis of a picture of the block in a picked up image and performs information processing. The play mat includes a play field that defines a detection space for the block, and a calibration chart including at least a plurality of regions of colors of different luminances. The image pickup apparatus adjusts an exposure time period, a gain value for each color component and a correction rule upon gamma correction on the basis of the picture of the calibration chart in the picked up image.

Abstract: Apparatus, systems and methods are provided for crop stand optimization. In some embodiments a field is planted at a first population prescription determined based on a first data set including forecasted weather. A subsequently determined second population prescription is determined based on a second data set determined after planting, and the planted crop is thinned according to the second population prescription. In some embodiments the crop is selectively thinned to remove plants having a plant removal index below a threshold.

Abstract: The invention relates to an end-effector device and automated selective thinning system. The system includes vision acquisition hardware, kinematic targeting and heuristic programming, a robotic arm, and a pomologically designed end-effector. The system is utilized to improve efficiency for the fruit-thinning process in a tree orchard, such as peach thinning By automating the mechanical process of fruit thinning, selective fruit-thinners can eliminate manual labor inputs and further enhance favorable blossom removal. Automation used in conjunction with a heuristic approach provides improvements to the system. The system may also be configured as a robotic arm or as a handheld system by including a battery and switching microcontroller with handle or wrist straps. Handheld thinning devices that are mechanical in nature may also be part of the system.

Abstract: The invention enables image processing of visible light and near-infrared light using an imaging device. An acquisition unit (110) acquires an image signal representing an image including near-infrared light that has an intensity according to a pattern having a prescribed geometric shape. A signal processing unit (120) uses pattern information which defines the pattern to output, a color signal representing visible light components corresponding to the image signal and a near-infrared signal representing near-infrared light components corresponding to the image signal.

Abstract: Systems and methods for determining body weight predictions and human conditions are disclosed. A body weight may be predicted by capturing at least one image of a human, and determining, from the image, a body weight prediction of the human by processing the at least one image with a data processor. The body weight prediction may further be based on an age-based weight factor. A model such as a neural network model may be used to predict body weight.

Abstract: A leg (205) detection system comprising: a robotic arm (200) comprising a gripping portion (208) for holding a teat cup (203, 210) for attaching to a teat (1102, 1104, 1106, 1108, 2038, 203) of a diary livestock (200, 202, 203); an imaging system coupled to the robotic arm (200) and configured to capture a first three-dimensional (3D) image (138, 2400, 2500) of a rearview of the dairy livestock (200, 202, 203) in a stall (402), the imaging system comprising a 3D camera (136, 138) or a laser (132), wherein each pixel of the first 3D image (138, 2400, 2500) is associated with a depth value; one or more memory (104) devices configured to store a reference (3D) 3D image (138, 2400, 2500) of the stall (402) without any dairy livestock (200, 202, 203); and a processor (102) communicatively coupled to the imaging system and the one or more memory (104) devices, the processor (102) configured to: access the first 3D image (138, 2400, 2500) and the reference (3D) 3D image (138, 2400, 2500); subtract the first 3D image

Abstract: An article conveying device, capable of selecting and taking out an appropriate article, even when plural articles are conveyed while overlapping each other. The device has: a supplying section for conveying articles; a position/orientation detecting section for detecting 3-D position/orientation of the article on the supplying section; a movement amount detecting section for detecting an amount of movement of the supplying section; a working section for taking out the article while following a conveying motion of the supplying section, based on the detected 3-D position/orientation and based on the detected amount of movement; and an article selecting section for, when the articles are conveyed while being overlapped with each other, selecting an article to be taken out, on which another article is not overlapped on the object in a determined take-out direction, and outputting a command to the working section for taking out the selected article.

Abstract: A system for observing agricultural samples includes a chassis suspended on an elevated cable or rail, an actuator disposed within the chassis for moving the chassis forward and backward along the elevated cable or rail, a camera mounted on or within the chassis and configured to acquire image data of an area below the elevated cable or rail including an agricultural sample, and a processor disposed within the chassis for receiving image data from the camera, autonomously controlling the actuator to move the chassis along the elevated cable or rail, and assessing a condition of the agricultural sample from the received image data.

Abstract: A method and an apparatus for background subtraction highly applicable in autonomous driving scenarios are described. The method involves a reduction of illumination effects by constructing a normality background image from a normality model based on a plurality of baseline images taken under different illuminating conditions. A subtracted image is obtained by subtracting the normality background image from a scene image pixel-wise (i.e., pixel-by-pixel). The scene image may contain one or more foreground objects. The foreground objects are identified by highlighting the pixels in the subtracted image whose intensity is more than a predetermined standard deviation in the normality model. An illumination-invariant color space transformation algorithm may optionally be utilized to further reduce the variant illumination effects.

Abstract: An object recognition apparatus includes an image capturing unit, a storage unit that stores feature data of a plurality of reference objects, a display unit, and a processor. The processor calculates degrees of similarity between an object in the captured image and a plurality of reference objects, based on the feature data of the reference objects, selects some of the reference objects as candidates objects based on the calculated degrees of similarity, and controls the display unit to display the candidate objects and a message to select one of the candidate objects. If no candidate object is selected within a predetermined time after the candidate objects and the message have been displayed, and thereafter a new image is captured by the image capturing unit, the processor removes the message and calculates degrees of similarity between an object in the newly captured image and the plurality of reference objects.

Abstract: A method and non-transitory computer readable medium for content based image retrieval. The method includes selecting a query image, segmenting the selected query image by applying a segmentation technique, extracting features from the segmented query image by determining at least two feature descriptors, including color feature descriptors and texture feature descriptors, and determining a similarity of the query image to a plurality of images included in a database using the determined at least two feature descriptors of the segmented query image, features being extracted from each of the plurality of images included in the database by determining the at least two feature descriptors, the color feature descriptors and the texture feature descriptors including a simultaneous combination of different color spaces, and global and local statistical measurements being carried out on the simultaneous combination of the different color spaces.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining an input including an image of a plant, identifying a species of the plant by use of visual recognition of the image. The image is analyzed for symptoms and candidate diagnoses are selected from a diagnostic repository according to the symptoms. With respective candidate diagnoses, a confidence score and a treatment regimen are associated. According to a treatment mode, the candidate diagnoses and treatment regimen are delivered.

Abstract: Slice representation of a volume with the aid of volume data is provided. A selection of a slice orientation for slice representation of volume data is made. A slice is then determined in accordance with the selected orientation. A relief representation is calculated for this slice and used as a relief for the representation of the at least one slice. A vivid representation of slice information is provided.

Abstract: According to one embodiment, a medical image processing apparatus is configured to capture images of an observation object over time to obtain a three-dimensional image. The observation object includes a first hard tissue and a second hard tissue which are adjacent to each other. The medical image processing apparatus includes a control circuit, a plane acquisition unit, and an image generator. Under the control of the control circuit, the plane acquisition unit extracts the first hard tissue and the second hard tissue based on the three-dimensional image. The image generator generates, as an image for observation, a cross-sectional image of a plane including the first hard tissue and at least part of the second hard tissue or an image projected on a plane parallel to the plane including the first hard tissue and at least part of the second hard tissue based on the three-dimensional image.

Abstract: This disclosure describes a system and a method for determining statistics of plant populations based on overhead optical measurements. The system may include one or more hardware processors configured by machine-readable instructions to receive output signals provided by one or more remote sensing devices mounted to an overhead platform. The output signals may convey information related to one or more images of a land area where crops are grown. The one or more hardware processors may be configured by machine-readable instructions to distinguish vegetation from background clutter; segregate image regions corresponding to the vegetation from image regions corresponding to the background clutter; and determine a plant count per unit area.

Abstract: A system and method for managing supply chain inventory which includes a product model to direct inventory management operations such as piece picking and restocking. The system includes a scanner configured to measure the dimensions and weight of a product, and to obtain a plurality of images of the product. The system further includes a computing device having at least one processor and a memory, and configured to use the measured weight and dimensions, and the plurality of images, to determine any of a shape of the outer surface of the product, a center of gravity of the product, and a three dimensional representation of a shape of a configuration of the product which may be included in the product model. Configurations can include single product, packaged product, and bundled configurations. The product model may be stored in memory or on a remote database for future use.

Abstract: A method for recognizing individual plants of a selected type growing in a field, wherein the method comprises capturing color NIR image data of an entire field having plants of a selected type growing therein utilizing an automated plant counting system and calculating a ratio value between each pixel of the color image data and the corresponding pixel of the NIR image data utilizing a plant recognition algorithm executed via a data processing system of the plant counting system. The method additionally comprises generating, via execution of the plant recognition algorithm, a false color image of the field based on the calculated ratios for each pixel, and identifying, via execution of the plant recognition algorithm, all plants of the selected type in the false color image based on a plant distinguishing characteristic uniquely rendered for each individual plant of the selected type in the false color image.

Abstract: Example image processing methods, apparatus/systems and articles of manufacture are disclosed herein. An example apparatus includes an image recognition application to identify matches between stored patterns and objects detected in a shelf image, where the shelf image has a shelf image scale estimate. The example apparatus further includes a scale corrector to calculate deviation values between sizes of (A) a first set of the objects detected in the shelf image and (B) a first set of the stored patterns matched with the first set of the objects and reduce an error of the shelf image scale estimate by calculating a scale correction value for the shelf image scale estimate based on the deviation values.

Abstract: A system and method for identifying developmental anomalies. The method includes obtaining a first set of at least one multimedia content element showing at least one crop and captured using a first set of at least one capturing parameter; obtaining normal development data for the at least one crop, wherein the normal development data represents at least one normal development characteristic of the at least one crop; analyzing, via machine vision, the first set of at least one multimedia content element to identify a first set of at least one characteristic of the at least one crop; determining, based on the first set of at least one characteristic and the normal development data, whether a suspected anomaly is identified; and verifying if the suspected anomaly is an anomaly using a second set of at least one multimedia content element captured using a second set of at least one capturing parameter.

Abstract: According to an aspect of the present application, a bird deterrence system is proposed comprising a laser device for producing a laser beam; comprising scanning equipment for rotating the laser beam at designated lateral and elevational angular speeds relative to the normal axis; a power supply for feeding the laser device and the scanning equipment; and a control unit for controlling the laser device and scanning equipment.

Abstract: The invention relates to a method for monitoring a meat processing machine having a meat processing unit for processing input meat products fed thereto into output meat products, an input sensor unit, and a control unit for controlling the meat processing unit, wherein the control unit is connected to the input sensor unit, comprising the steps: feeding input meat products to the meat processing unit, acquiring input product data, in particular geometric data and/or weight data, of the input meat product fed to the meat processing unit by means of the input sensor unit, and determining a tolerance variable for a yield-relevant processing parameter by means of a mathematical model or a database, in each case depending on the acquired input product data. The invention further relates to a meat processing machine for performing the method.

Abstract: Methods and systems are presented for making good use of recently obtained biometric data and for configuring propagule capsules for deployment via an unmanned vehicle so that each has an improved chance of survival.

Abstract: In one embodiment, a fluorescence histo-tomography (FHT) system is disclosed. The FHT system includes a housing, a fluorescence camera located within the housing, a white light camera located within the housing, and a fluorescence light source located within the housing. The FHT system further includes a support mount configured to support the housing within a chamber of a slicing apparatus such that the cameras and fluorescence light source are aimed towards a block face of a tissue specimen retained within the chamber.

Abstract: At least one sensor carried by a mobile machine senses a sensed forage crop attribute value independent of plant population for an individual forage plant. A processing unit derives a derived forage crop attribute value based on the sensed forage crop attribute value.

Abstract: A rover includes a base having wheels and a propulsion system coupled to the wheels to propel the rover around a field. A tower is coupled to the base and extends over the base. Sensors are set on the tower and the base and are configured to sense environmental conditions around the rover at different elevations. A computing system includes a processor and memory. The memory is configured to receive measured data from the sensors and determine an amount and manner of water to be dispensed on plant life in the field.

Abstract: A non-invasive biometrical identification method and system (100) of animals, comprising: receiving characteristic data of an individual from at least one biometric sensor (102); processing the characteristic data to form biometric data identifying minutiae based skin markings of the individual and biometric data identifying physical characteristics of the individual; evaluating the biometric data identifying minutiae based skin markings of the individual and biometric data identifying physical characteristics of the individual to form biometric characteristic data of the individual; comparing the biometric characteristic findings of the individual to characteristic data of predetermined registered individuals; determining whether the individual is registered; giving the individual a unique identification if the individual is not registered; and registering the unique identification in a data storage (112).

Abstract: According to one embodiment, there is provided a quality controlling device including: a predictor, a frequency calculator, and an implementing signal creator. The predictor employs a prediction model that associates an inspection result value of a first inspection with a predicted value being a value relating to a possibility of pass or failure in a second inspection and calculates the predicted value from an inspection result value that is obtained for an inspection target in the first inspection. The frequency calculator calculates, for the inspection target, an implementation frequency to implement the second inspection in accordance with the predicted value calculated by the predictor. The implementing signal creator creates a signal that indicates, for the inspection target, necessity of implementing the second inspection in accordance with the implementation frequency.

Abstract: Methods and systems are presented for obtaining photographic data recently taken via one or more airborne vehicles (drones, e.g.) and for prioritizing forestry-related review and decision-making as an automatic response to the content of the photographic data even where remote decision-makers are only available via limited-bandwidth connections.

Abstract: Systems and methods are disclosed for deep learning and classifying images of objects by receiving images of objects for training or classification of the objects; producing fine-grained labels of the objects; providing object images to a multi-class convolutional neural network (CNN) having a softmax layer and a final fully connected layer to explicitly model bipartite-graph labels (BGLs); and optimizing the CNN with global back-propagation.

Abstract: An image acquisition unit acquires an image including an object, and a controller starts a visual servo using the acquired image, on the basis of at least one of an error in calibration, an error in installation of a robot, an error resulting from the rigidity of the robot, an error of a position where the robot has gripped the object, an error regarding imaging, and an error regarding a work environment. Additionally, the controller starts the visual servo when the distance between one point of a working unit of the robot and the object is equal to or greater than 2 mm.

Abstract: A method of monitoring an infectious disease, a system using the same, and a recording medium for performing the same are provided. The infectious disease monitoring system includes an imaging device for capturing and transmitting image data on animals managed in a barn, a first server for determining whether a subject suspected of having an infectious disease is detected from the image data and, when the subject suspected of having the infectious disease is detected, transmitting a signal along with the image data, a second server for confirming an occurrence of the infectious disease by analyzing the image data of the subject suspected of having the infectious disease, and transmitting a warning signal when confirmed the occurrence of the infectious disease, and a manager terminal for requesting the image data on the animals to the first server upon receipt of the warning signal and displaying the image data.

Abstract: A system includes a robotic arm, an imaging device coupled to the robotic arm, a tail positioner coupled to the robotic arm, and a processor. The imaging device captures imaging data of a rearview of a dairy livestock through a field of view of the imaging device. The tail positioner is able to move from a down position to an up position. The processor is coupled to both the imaging device and the tail positioner and is configured to identify a tail of the dairy livestock within the imaging data captured by the imaging device and send one or more instructions to raise the tail positioner from the down position to the up position, thereby moving the tail out of the field of view of the imaging device.

Abstract: An example plant monitoring system can include sensors connected to a horticultural monitor. The sensors can measure the soil, the environment, individual plant characteristics, etc. At least one horticultural monitor can send sensor data to a local beacon. The local beacon can then receive the data and send it to cloud resources which can process the data. The cloud resources can determine the health of the plant and monitor its development. A user can track this health and development using an interaction device.

Abstract: Disclosed are object detection method, display methods and apparatuses. The method includes obtaining slice data of inspected luggage in the CT system; generating 3D volume data of objects in the luggage from the slice data; for each object, determining a semantic description including at least a quantifier description of the object based on the 3D volume data; and upon reception of a user selection of an object, presenting the semantic description of the selected object while displaying a 3D image of the object. The above solutions can create a 3D model for objects in the inspected luggage in a relatively accurate manner, and thus provide better basis for subsequent shape feature extraction and security inspection, and reduce omission factor.