Abstract: Described herein are systems and methods that improve the success rate of relocalization and eliminate the ambiguity of false relocalization by exploiting motions of the sensor system. In one or more embodiments, during a relocalization process, a snapshot is taken using one or more visual sensors and a single-shot relocalization in a visual map is implemented to establish candidate hypotheses. In one or more embodiments, the sensors move in the environment, with a movement trajectory tracked, to capture visual representations of the environment in one or more new poses. As the visual sensors move, the relocalization system tracks various estimated localization hypotheses and removes false ones until one winning hypothesis. Once the process is finished, the relocalization system outputs a localization result with respect to the visual map.

Abstract: Described herein are systems and methods for object detection to achieve hard real-time performance with low latency. Real-time object detection frameworks are disclosed. In one or more embodiments, a framework comprises a first CPU core, a second CPU core, and a plurality of shaves. In one or more embodiments, the first CPU core handles general CPU tasks, while the second CPU core handles the image frames from a camera sensor and computation task scheduling. In one or more embodiments, the scheduled computation tasks are implemented by the plurality of shaves using at least one object-detection model to detect an object in an image frame. In one or more embodiments, computation results from the object-detection model with a higher detection probability is used to form an output for object detection. In one or more embodiments, the object-detection models share some parameters for smaller size and higher implementing speed.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for compressing a deep learning model. An embodiment of the method includes: acquiring a to-be-compressed deep learning model; pruning each layer of weights of the to-be-compressed deep learning model in units of channels to obtain a compressed deep learning model; and sending the compressed deep learning model to a terminal device, so that the terminal device stores the compressed deep learning model. By pruning each layer of weights of the deep learning model in units of channels, the parameter redundancy of the deep learning model is effectively reduced, thereby improving the computational speed of the deep learning model and maintaining the model accuracy.

Abstract: Described herein are embodiments of a deep residual network dedicated to color filter array mosaic patterns. A mosaic stride convolution layer is introduced to match the mosaic pattern of a multispectral filter arrays (MSFA) or a color filter array raw image. Embodiments of a data augmentation using MSFA shifting and dynamic noise are applied to make the model robust to different noise levels. Embodiments of network optimization criteria may be created by using the noise standard deviation to normalize the L1 loss function. Comprehensive experiments demonstrate that embodiments of the disclosed deep residual network outperform the state-of-the-art denoising algorithms in MSFA field.

Abstract: A method for information processing for accelerating neural network training. The method includes: acquiring a neural network corresponding to a deep learning task; and performing iterations of iterative training on the neural network based on a training data set. The training data set includes task data corresponding to the deep learning task. The iterative training includes: processing the task data in the training data set using a current neural network, and determining, based on a processing result of the neural network on the task data in a current iterative training, prediction loss of the current iterative training; determining a learning rate and a momentum in the current iterative training; and updating weight parameters of the current neural network by gradient descent based on a preset weight decay, and the learning rate, the momentum, and the prediction loss in the current iterative training. This method achieves efficient and low-cost deep learning-based neural network training.

Abstract: Embodiments of the present disclosure provide a method and apparatus for identifying an item. The method includes: acquiring an item image of a to-be-identified item; setting initial position coordinates of the to-be-identified item on the item image; and executing following identifying: inputting the item image and the initial position coordinates into a pre-trained attention module to output an item feature of the to-be-identified item; inputting the item feature into a pre-trained long short-term memory network to output a predicted category and predicted position coordinates of the to-be-identified item; determining whether a preset condition is satisfied; and determining, in response to the preset condition being satisfied, a predicted category of the to-be-identified item outputted by the long short-term memory network a last time for use as a final category of the to-be-identified item.

Abstract: The disclosure provides human-tracking methods, systems, and storage media. The method includes: acquiring a plurality of human point clouds of a current frame from a plurality of cameras; generating a total point cloud of the current frame by integrating the plurality of human point clouds of the current frame; acquiring a plurality of human point clouds of a next frame from the plurality of cameras; acquiring a total point cloud of the next frame by integrating the plurality of human point clouds of the next frame; and performing human tracking based on the total point cloud of the current frame and the total point cloud of the next frame.

Abstract: The present disclosure provides a method and a device for recognizing a product, an electronic device and a non-transitory computer readable storage medium, relating to a field of unmanned retail product recognition. The method includes the following. A video taken by each camera in a store is acquired. A recognition is performed on each video to obtain a video segment that a product delivery is recognized and to obtain participated users. The participated users include a delivery initiation user and a delivery reception user. The video segment is inputted into a preset delivery recognition model to obtain a recognition result. The recognition result includes a product delivered and a delivery probability. The product information of products carried by the participated users is updated based on the recognition result.

Abstract: Embodiments disclose an artificial intelligence chip and a convolutional neural network applied to the artificial intelligence chip comprising a processor, at least one parallel computing unit, and a pooling computation unit. The method comprises: dividing a convolution task into convolution subtasks and corresponding pooling subtasks; executing convolution subtasks at different parallel computing units, and performing convolution, batch normalization, and non-linear computing operation in a same parallel computing unit; sending an execution result of each parallel computing unit from executing the convolution subtask to the pooling computation unit for executing the corresponding pooling subtask; merging executing results of the pooling computation unit from performing pooling operations on the executing results outputted by respective convolution subtasks to obtain an execution result of the convolution task.

Abstract: Described herein are systems and embodiments for multispectral image demosaicking using deep panchromatic image guided residual interpolation. Embodiments of a ResNet-based deep learning model are disclosed to reconstruct the full-resolution panchromatic image from multispectral filter array (MSFA) mosaic image. In one or more embodiments, the reconstructed deep panchromatic image (DPI) is deployed as the guide to recover the full-resolution multispectral image using a two-pass guided residual interpolation methodology. Experiment results demonstrate that the disclosed method embodiments outperform some state-of-the-art conventional and deep learning demosaicking methods both qualitatively and quantitatively.

Abstract: The present disclosure provides a human body recognition method and apparatus, and a storage medium, the method comprising: determining a coordinate of a target person in a three-dimensional space according to images containing the target person collected by at least two cameras; calculating back-projection errors of the target person under different cameras respectively according to the coordinate of the target person in the three-dimensional space; determining whether the cameras have a human body recognition error according to the back-projection errors of the cameras; when a camera has the human body recognition error, performing re-recognition of the target person under the camera by using person re-identification ReID, until the back-projection errors of all the cameras containing the target person are not greater than a preset threshold. The present disclosure can improve accuracy of the human body recognition result effectively.

Abstract: A human body tracking method, apparatus, and device, and a storage medium. The method includes: obtaining a current frame image captured by a target photographing device at a current moment; detecting each human body in the current frame image to obtain first position information of the each human body in the current frame image; calculating second position information of a first human body in the current frame image; determining target position information of the each human body in the current frame image according to the second position information of the first human body in the current frame image, the first position information of the each human body in the current frame image, and pedestrian features of all tracked pedestrians stored in a preset list.

Abstract: Embodiments of the present disclosure provide a method and apparatus for generating information, a device for human-computer interaction, and a computer readable medium. The method may include: acquiring gravity sensing data of a shelf carrying an item; and identifying, in response to determining that the item on the shelf is taken based on the gravity sensing data, the taken item based on the gravity sensing data and an acquired image of the taken item, and generating order information of the taken item.

Abstract: A method, apparatus, device, and storage medium for predicting the number of people of a dense crowd, including: converting a first image, in which the number of people is to be determined, into a corresponding first thermodynamic chart according to a thermodynamic chart conversion model; and determining the number of people in the first image according to the first thermodynamic chart, wherein the thermodynamic chart conversion model is obtained by training according to a pre-marked second image and a thermodynamic chart corresponding to each second image, thereby achieving prediction of the number of people of a dense crowd, improving the accuracy in predicting the number of people of the dense crowd while improving management efficiency.

Abstract: A method, apparatus and a system for human body tracking processing, where an apparatus for video collection processing in the system has a built-in intelligent chip, and before uploading video data to a cloud server, the intelligent chip performs a pre-processing on the video data, retains a key image frame and performs a human body detection and a tracking processing on the key image frame by using human body detection tracking algorithm to acquire a first human body detection tracking result. Afterwards, the intelligent chip sends the first human body detection tracking result to the cloud server, so that the cloud server performs a human body re-identification algorithm processing and/or three-dimensional reconstruction algorithm processing on the first human body detection tracking result to acquire a second human body detection tracking result.

Abstract: Described herein are systems and methods that allow for dense depth map estimation given input images. In one or more embodiments, a neural network model was developed that significantly differs from prior approaches. Embodiments of the deep neural network model comprises more computationally efficient structures and fewer layers but still produces good quality results. Also, in one or more embodiments, the deep neural network model may be specially configured and trained to operate using a hardware accelerator component or components that can speed computation and produce good results, even if lower precision bit representations are used during computation at the hardware accelerator component.

Abstract: Described herein are systems and methods that involve abnormality detection and a carefully designed state machine that assesses whether mapping, such as simultaneous localization and mapping (SLAM) processing, should be skipped for the current image frames, whether relocalization may performed, or whether SLAM processing may be performed. Thus, embodiments allow mapping processing to timely and smoothly switch between different tracking states, and thereby prevent bad tracking status to occur.

Abstract: Presented herein are embodiments of a training deep learning models. In one or more embodiments, a compact deep learning model comprises fewer layers, which require fewer floating-point operations (FLOPs). Presented herein are also embodiments of a new learning rate function, which can adaptively change the learning rate between two linear functions. In one or more embodiments, combinations of half-precision floating point format training together with larger batch size in the training process may also be employed to aid the training process.

Abstract: Embodiments herein treat the action segmentation as a domain adaption (DA) problem and reduce the domain discrepancy by performing unsupervised DA with auxiliary unlabeled videos. In one or more embodiments, to reduce domain discrepancy for both the spatial and temporal directions, embodiments of a Mixed Temporal Domain Adaptation (MTDA) approach are presented to jointly align frame-level and video-level embedded feature spaces across domains, and, in one or more embodiments, further integrate with a domain attention mechanism to focus on aligning the frame-level features with higher domain discrepancy, leading to more effective domain adaptation. Comprehensive experiment results validate that embodiments outperform previous state-of-the-art methods. Embodiments can adapt models effectively by using auxiliary unlabeled videos, leading to further applications of large-scale problems, such as video surveillance and human activity analysis.

Abstract: An information processing method, a device, a system, and a storage medium. The information processing method includes: an AI camera first obtains real-time data in a unmanned retail scenario and performs a front-end processing on the real-time data based on a neural network model, where the front-end processing includes any one or more of commodity identifying and human body monitoring, and then transmits a result of the front-end processing to a server, where the result of the front-end processing is used to trigger the server to perform face recognition and/or determine a flow direction of a commodity according to the result of the front-end processing. The cost of the entire unmanned retail distributed system and the pressure on data transmission bandwidth can be reduced, and system scalability as well as the performance of the solution to the unmanned retail can be improved effectively.