Abstract: Visual analytics tool for updating object detection models in autonomous driving applications. In one embodiment, an object detection model analysis system including a computer and an interface device. The interface device includes a display device. The computer includes an electronic processor that is configured to extract object information from image data with a first object detection model, extract characteristics of objects from metadata associated with image data, generate a summary of the object information and the characteristics, generate coordinated visualizations based on the summary and the characteristics, generate a recommendation graphical user interface element based on the coordinated visualizations and a first one or more user inputs, and update the first object detection model based at least in part on a classification of one or more individual objects as an actual weakness in the first object detection model to generate a second object detection model for autonomous driving.

Abstract: A system includes a camera configured to obtain image information from objects. The system also includes a processor in communication with the camera and programmed to receive an input data including the image information, encode the input via an encoder, obtain a latent variable defining an attribute of the input data, generate a sequential reconstruction of the input data utilizing at least the latent variable and an adversarial noise, obtain a residual between the input data and the sequential reconstruction utilizing a comparison of at least the input and the reconstruction to learn a mean shift in latent space, and output a mean shift indicating a test result of the input compared to the adversarial noise based on the comparison.

Abstract: A system includes a camera configured to obtain image information from objects. The system also includes a processor in communication with the camera and programmed to receive an input data including the image information, encode the input via an encoder, obtain a latent variable defining an attribute of the input data, generate a sequential reconstruction of the input data utilizing at least the latent variable and an adversarial noise, obtain a residual between the input data and the sequential reconstruction utilizing a comparison of at least the input and the reconstruction to learn a mean shift in latent space, and output a mean shift indicating a test result of the input compared to the adversarial noise based on the comparison.

Abstract: A mobile robotic device receives point cloud data corresponding to an internal space of a facility and processes the data to generate a map of the facility that enables the mobile robotic device to move within the internal space. The processing of the point cloud data includes segmentation of the data into planar primitives that are identified as ceiling, floor, or wall primitives. Openings in the wall primitives are identified as doors or occlusions. Viewpoints for the processed planar primitives are generated and a complex cell data structure is generated with vertices representing faces of the structure and edges representing walls. After an energy minimization of the complex cell structure is performed, adjacent regions of space are evaluated for merger and a map of the internal space is generated. The mobile robotic device moves through the internal space of the facility with reference to the map.

Abstract: Visual analytics tool for updating object detection models in autonomous driving applications. In one embodiment, an object detection model analysis system including a computer and an interface device. The interface device includes a display device. The computer includes an electronic processor that is configured to extract object information from image data with a first object detection model, extract characteristics of objects from metadata associated with image data, generate a summary of the object information and the characteristics, generate coordinated visualizations based on the summary and the characteristics, generate a recommendation graphical user interface element based on the coordinated visualizations and a first one or more user inputs, and update the first object detection model based at least in part on a classification of one or more individual objects as an actual weakness in the first object detection model to generate a second object detection model for autonomous driving.

Abstract: Weaknesses may be exposed in image object detectors. An image object is overlaid onto a background image at each of a plurality of locations, the background image including a scene in which the image objects can be present. A detector model is used to attempt detection of the image object as overlaid onto the background image, the detector model being trained to identify the image object in background images, the detection resulting in background scene detection scores indicative of likelihood of the image object being detected at each of the plurality of locations. A detectability map is displayed overlaid on the background image, the detectability map including, for each of the plurality of locations, a bounding box of the image object illustrated according to the respective detection score.

Abstract: Weaknesses may be exposed in image object detectors. An image object is overlaid onto a background image at each of a plurality of locations, the background image including a scene in which the image objects can be present. A detector model is used to attempt detection of the image object as overlaid onto the background image, the detector model being trained to identify the image object in background images, the detection resulting in background scene detection scores indicative of likelihood of the image object being detected at each of the plurality of locations. A detectability map is displayed overlaid on the background image, the detectability map including, for each of the plurality of locations, a bounding box of the image object illustrated according to the respective detection score.

Abstract: A method for tire inspection which includes taking at least one image of at least one first area of a tread of a tire that is to be inspected; determining the profile depth of a second area of the tread of the tire, the second area being included in the first area; and displaying the profile depth of the at least one image of the at least one first area and the position of the second area in the first area. The method may additionally include automatically analyzing the images taken of the tread, so as to arrive at statements on the condition of the tread.

Abstract: An installation for hot dip coating a metal strip is provided. The installation includes a device for moving the metal strip along a path, a pot for containing a melt bath and a wiping system including at least two nozzles placed on either side of the path downstream the pot. The wiping system has a box with a lower confinement part confining an atmosphere around the metal strip upstream of said nozzles and an upper confinement part confining the atmosphere around the metal strip downstream of the nozzles, first moving means for vertically moving the lower confinement part with respect to the pot and second moving means for vertically moving the upper confinement part with respect to both the pot and the lower confinement part. The nozzles are vertically movable relative to the pot.

Abstract: A mobile robotic device receives point cloud data corresponding to an internal space of a facility and processes the data to generate a map of the facility that enables the mobile robotic device to move within the internal space. The processing of the point cloud data includes segmentation of the data into planar primitives that are identified as ceiling, floor, or wall primitives. Openings in the wall primitives are identified as doors or occlusions. Viewpoints for the processed planar primitives are generated and a complex cell data structure is generated with vertices representing faces of the structure and edges representing walls. After an energy minimization of the complex cell structure is performed, adjacent regions of space are evaluated for merger and a map of the internal space is generated. The mobile robotic device moves through the internal space of the facility with reference to the map.

Abstract: A device for testing a vehicle includes at least one sound recording device, which is designed for recording the sound emitted by a vehicle to be tested, and an evaluation device, which is designed for evaluating the sound recorded by the at least one sound recording device. The device may include at least one image recording device, which is designed for recording at least one image of the vehicle to be tested, and a display device which is designed for representing the source(s) of the recorded sound in at least one image of the vehicle to be tested.

Abstract: A device for optically recording the underbody of a vehicle using at least one camera, includes at least two mirrors which are disposed and oriented in such a way that images of several areas of the underbody of the vehicle are able to be recorded simultaneously by the camera.

Abstract: An installation for hot dip coating a metal strip is provided. The installation includes a device for moving the metal strip along a path, a pot for containing a melt bath and a wiping system including at least two nozzles placed on either side of the path downstream the pot. The wiping system has a box with a lower confinement part confining an atmosphere around the metal strip upstream of said nozzles and an upper confinement part confining the atmosphere around the metal strip downstream of the nozzles, first moving means for vertically moving the lower confinement part with respect to the pot and second moving means for vertically moving the upper confinement part with respect to both the pot and the lower confinement part. The nozzles are vertically movable relative to the pot.

Abstract: A method for adjusting and/or calibrating a surroundings sensor in a vehicle using a measuring unit and a calibration panel.

Abstract: A method for determining distances for chassis measurement of a vehicle having a body and at least one wheel includes determining a center of rotation of a wheel of the vehicle by projecting a structured light pattern at least onto the wheel, recording a light pattern reflected by the wheel using a calibrated imaging sensor system, determining a 3D point cloud from the reflected light pattern, and determining the center of rotation of the wheel from the 3D point cloud. The method also includes determining a point on the body by evaluating the previously determined 3D point cloud or by evaluating a plurality of grey-scale images recorded under unstructured illumination. A height level is determined as a vertical distance between the center of rotation of the wheel and the point on the body.

Abstract: A device for testing a vehicle includes at least one sound recording device, which is designed for recording the sound emitted by a vehicle to be tested, and an evaluation device, which is designed for evaluating the sound recorded by the at least one sound recording device. The device may include at least one image recording device, which is designed for recording at least one image of the vehicle to be tested, and a display device which is designed for representing the source(s) of the recorded sound in at least one image of the vehicle to be tested.

Abstract: A method for tire inspection which includes taking at least one image of at least one first area of a tread of a tire that is to be inspected; determining the profile depth of a second area of the tread of the tire, the second area being included in the first area; and displaying the profile depth of the at least one image of the at least one first area and the position of the second area in the first area. The method may additionally include automatically analyzing the images taken of the tread, so as to arrive at statements on the condition of the tread.

Abstract: A device for optically recording the underbody of a vehicle using at least one camera, includes at least two mirrors which are disposed and oriented in such a way that images of several areas of the underbody of the vehicle are able to be recorded simultaneously by the camera.

Abstract: A method for rectifying a camera image includes: receiving a plurality of distorted pixels of a distorted camera image; receiving a compressed rectifying rule, via an interface; and performing a decompression of the compressed rectifying rule, in order to obtain a decompressed rectifying rule for rectifying the distorted camera image. A plurality of rectified pixels of a distorted camera image is determined from the plurality of distorted pixels, using the decompressed rectifying rule.

Abstract: A chassis measuring system comprises an illumination device for producing a structured illumination (38, 58, 78, 98), which is developed in such a way that it produces a structured image on a measuring head (32, 52; 72, 92) situated opposite in the transverse vehicle direction, a reference surface (40, 60, 80, 100) facing in the same direction as the illumination device (38, 58, 78, 98), on which a structured image produced by an illumination device (38, 58; 78, 98) of the measuring head (32, 52; 72, 92) situated opposite in the transverse vehicle direction may be projected, and at least one measuring camera (34, 36; 54, 56; 74, 76; 94, 96) facing in the same direction as the illumination device (38, 58, 78, 98), which is developed in such a way that it detects the structured image on the reference surface (40, 60; 80, 100) of the opposite measuring head (32, 52; 72, 92) in order to determine the position parameters of the measuring head (32, 52, 72, 92).