Abstract: Techniques for monitoring particulate matter (PM) mass concentration using relatively low cost devices are described. A computer-implemented method comprises determining, by a device operatively coupled to a processor, relationships between: first PM mass data determined by a monitor station device for a first atmospheric area over a period of time; first PM count data determined by a reference PM count device for the first atmospheric area over the period of time; and first conditional information comprising first values for defined conditional parameters, wherein the first values are associated with the first atmospheric area over the period of time. The method further includes generating an initial conversion model based on the relationships, wherein the conversion model converts a PM count to a PM mass based on one or more conditional parameters of the defined conditional parameters and features for updating the conversion model.

Abstract: In some examples, a method includes receiving an artificial intelligence (AI) system scenario definition file from a user, parsing the definition file and building an application workflow graph for the AI system, and mapping the application workflow graph to an execution pipeline. In some examples, the method further includes automatically generating, from the workflow graph, application executable binary code implementing the AI system, and outputting the application executable binary code to the user. In some examples, the execution pipeline includes one or more building blocks, and the method then further includes collecting running performance of each of the building blocks of the execution pipeline in a runtime environment.

Abstract: A method, computer system and computer program product for model compression service. The method comprises determining an initial deep neural network (DNN) and an associated compression algorithm available in a compression engine, a type of target hardware and a performance requirement of target hardware. The method also comprises emulating a plurality of different compressed models of the initial DNN on target hardware of the type to obtain corresponding runtime performance data, wherein the different compressed models are defined with different configuration data. The method further comprises obtaining a runtime performance estimator of the target hardware by regression with the different configuration data and the corresponding runtime performance data. Lastly, the method comprises applying the runtime performance estimator to the compression algorithm by the compression engine to generate a compressed DNN of the initial DNN complying with the performance requirement of the type of target hardware.

Abstract: The present disclosure relates to methods, systems, and computer program products for implementing a deep neural network in a field-programmable gate array (FPGA). In response to receiving a network model describing a deep neural network, a plurality of layers associated with the deep neural network may be determined. With respect to a layer in the plurality of layers, a parallelism factor for processing operations associated with the layer simultaneously by processing elements in an FPGA may be determined based on a workload associated with the layer and a configuration of the FPGA.

Abstract: A method for configuring a set of hardware accelerators to process a CNN. In an embodiment, the method includes one or more computer processors determining a set of parameters related to a feature map to analyze at a respective layer of the CNN, the set of parameters include quantization value and respective values that describe a shape of the feature map. The method further includes configuring a set of hardware accelerators for the respective layer of the CNN. The method further includes receiving a portion of the feature map to the configured set of hardware accelerators for the respective layer of the CNN, wherein the received portion of the feature map includes a group of sequential data slices. The method further includes analyzing the group of sequential data slices among the configured set of hardware accelerators.

Abstract: Techniques for unattended object detection using machine learning are disclosed. A machine learning policy, for use in identifying unattended objects in a captured image depicting one or more objects, is generated. The generating includes determining a level of occlusion in the captured image relating to the objects, and determining the machine learning policy based on the determined level of occlusion. A machine learning model is selected, from among a plurality of pre-defined machine learning models, based on the generated machine learning policy. An unattended object is detected in the captured image using the selected machine learning model.

Abstract: According to one embodiment, a method, computer system, and computer program product for generating anchors and selecting feature maps for a multi-scale object detection program based on analysis of the dataset is provided. The present invention may include generating a scale distribution of one or more scales of ground-truth objects, and, based on the scale distribution, dividing the effective scale range into a number of anchors greater than zero; furthermore, the invention may include generating a ratio distribution of ratios of the ground-truth objects; based on the ratio distribution, generating a ratio for at least one of the number of anchors; determining a template scale of one or more feature maps; and assigning the number of anchors to the feature maps based on the relative size of a scale of an anchor matching the relative size of a template scale of a feature map.

Abstract: A method for sending early warning information, a storage medium and a terminal are provided. The method includes: calculating a target similarity between a first face image and a target face image when the first face image captured by an imaging device is acquired; and generating and sending early warning information corresponding to the first face image if the target similarity reaches a similarity threshold at the current moment; wherein, the similarity threshold is determined by a fluctuation degree value of a plurality of similarities in a similarity sample, the similarity in the similarity sample is a target similarity corresponding to a generated warning information, and the similarity sample is updated over. As a result, the accuracy in early warning may be improved.

Abstract: In an approach for detecting queuing information, a processor analyzes a video monitoring a queue area. A processor detects a queue barrier in the queue area using an instance segmentation technique based on the video. A processor identifies a queue in the queue area using a heuristic technique. A processor recognizes a number of people in the queue. A processor provides an estimation of a wait time for the queue.

Abstract: A method, system, and computer program product for detecting multi-scale objects. The method may include receiving a sample dataset including multi-scale objects associated with a specific environment, where the sample dataset has an existing resolution. The method may also include inputting the sample dataset into a trained neural network, where the trained neural network has a plurality of scale regions. The method may also include processing the sample dataset for detecting the multi-scale objects by means of the trained neural network. The method may also include calculating a distribution of contribution degree in a course of processing the sample dataset, where the contribution degree is associated with each of the plurality of scale regions. The method may also include generating a set of configuration parameters associated with the specific environment for the trained neural network based at least in part on the distribution of contribution degree.

Abstract: Techniques for unattended object detection using machine learning are disclosed. A machine learning policy, for use in identifying unattended objects in a captured image depicting one or more objects, is generated. The generating includes determining a level of occlusion in the captured image relating to the objects, and determining the machine learning policy based on the determined level of occlusion. A machine learning model is selected, from among a plurality of pre-defined machine learning models, based on the generated machine learning policy. An unattended object is detected in the captured image using the selected machine learning model.

Abstract: According to one embodiment, a method, computer system, and computer program product for generating anchors and selecting feature maps for a multi-scale object detection program based on analysis of the dataset is provided. The present invention may include generating a scale distribution of one or more scales of ground-truth objects, and, based on the scale distribution, dividing the effective scale range into a number of anchors greater than zero; furthermore, the invention may include generating a ratio distribution of ratios of the ground-truth objects; based on the ratio distribution, generating a ratio for at least one of the number of anchors; determining a template scale of one or more feature maps; and assigning the number of anchors to the feature maps based on the relative size of a scale of an anchor matching the relative size of a template scale of a feature map.

Abstract: The present disclosure provides a computer-implemented method, computer system and computer program product for object detection. According to the computer-implemented method, a first object can be classified to be a first category based on detection data acquired in a detection area. Then, a confidence score for the first category can be calculated based on historical detection data of the detection area, wherein the confidence score presents possibility degree of at least one object of the first category existing in the detection area. Whether classification of the first object is abnormal can be determined based on the confidence score.

Abstract: A method, computer system, and computer program product for model selection for training a new dataset is provided. The present invention may include choosing a model from a set of models to be evaluated for training the new dataset, selecting a sample input from a subset of the new dataset, calculating a model activation score for each of the sample inputs in the chosen model, calculating an accumulated model activation score for the chosen model, depending on the model activation score of each of the sample inputs in the chosen model, calculating an accumulated model activation score for each model from the set of models to be evaluated for training the new dataset, and selecting the model for training the new dataset with the highest accumulated model activation score.

Abstract: In some examples, a method includes receiving an artificial intelligence (AI) system scenario definition file from a user, parsing the definition file and building an application workflow graph for the AI system, and mapping the application workflow graph to an execution pipeline. In some examples, the method further includes automatically generating, from the workflow graph, application executable binary code implementing the AI system, and outputting the application executable binary code to the user. In some examples, the execution pipeline includes one or more building blocks, and the method then further includes collecting running performance of each of the building blocks of the execution pipeline in a runtime environment.

Abstract: A method, system, and computer program product for detecting multi-scale objects. The method may include receiving a sample dataset including multi-scale objects associated with a specific environment, where the sample dataset has an existing resolution. The method may also include inputting the sample dataset into a trained neural network, where the trained neural network has a plurality of scale regions. The method may also include processing the sample dataset for detecting the multi-scale objects by means of the trained neural network. The method may also include calculating a distribution of contribution degree in a course of processing the sample dataset, where the contribution degree is associated with each of the plurality of scale regions. The method may also include generating a set of configuration parameters associated with the specific environment for the trained neural network based at least in part on the distribution of contribution degree.

Abstract: Techniques for monitoring particulate matter (PM) mass concentration using relatively low cost devices are described. A computer-implemented method comprises determining, by a device operatively coupled to a processor, relationships between: first PM mass data determined by a monitor station device for a first atmospheric area over a period of time; first PM count data determined by a reference PM count device for the first atmospheric area over the period of time; and first conditional information comprising first values for defined conditional parameters, wherein the first values are associated with the first atmospheric area over the period of time. The method further includes generating an initial conversion model based on the relationships, wherein the conversion model converts a PM count to a PM mass based on one or more conditional parameters of the defined conditional parameters and features for updating the conversion model.

Abstract: In an approach for detecting queuing information, a processor analyzes a video monitoring a queue area. A processor detects a queue barrier in the queue area using an instance segmentation technique based on the video. A processor identifies a queue in the queue area using a heuristic technique. A processor recognizes a number of people in the queue. A processor provides an estimation of a wait time for the queue.

Abstract: A computer implemented method of detecting excessive customer wait times is provided. The method includes taking a headcount in a digital image obtained by a digital video camera of a monitored area, counting the number of bodies in the digital image, and rectifying the number of heads with the number of bodies to obtain a total count of persons. The method further includes determining which persons are moving and subtracting the moving persons from the total count of persons to obtain a still count, and determining which persons are workers and subtracting the workers from the still count to identify customers in the monitored area and obtain a customer count. The method further includes identifying the number of queues present in the monitored area, assigning each customer to a queue, and determining the wait time for each of the identified customers in each of the identified queues.

Abstract: A method includes obtaining a first set of parameters corresponding to a first video, such parameters including a first skip number and a first segment length. The method includes obtaining a first set of image feature values corresponding to the first video and storing the first set of parameters and the first set of image feature values as reference data. The method includes calculating a second set of image feature values corresponding to a second video and comparing the second set of image feature values to the reference data, and determining, based on the comparing, that the second set of image feature values exceeds a threshold. The method includes calculating, in response to the determining, a variance. The method includes generating, based on the variance, a second set of parameters corresponding to the second video, the second set of parameters including a second skip number and a second segment length.