The present application provides an action recognition method and apparatus and an electronic device. The method includes: if a target object is detected from a video frame, acquiring a plurality of images containing the target object, and optical-flow images of the plurality of images; extracting an object trajectory feature of the target object from the plurality of images, and extracting an optical-flow trajectory feature of the target object from the optical-flow images of the plurality of images; and according to the object trajectory feature and the optical-flow trajectory feature, recognizing a type of an action of the target object. Because it combines the time-feature information and the spatial-feature information of the target object, effectively increases the accuracy of the detection and recognition on the action type, and may take into consideration the detection efficiency at the same time, thereby improving the overall detection performance.

Provided are a device and a method which enable easy analysis and evaluation of work efficiency of a worker without burdensome tasks and easy determination of a worker's skill level by comparing the worker's work efficiency status with that of another worker or a past record of the same worker, wherein analytical information is produced by estimating the worker's joint positions based on a video; acquiring time series data on joint positions; determining work efficiency based on the time series data; acquiring a target range (part of a work process with low work efficiency); output an image of the target range overlaid on a graph of the time series data; and output a posture image of the worker overlaid on the video. The analytical information may include information on a working activity to be analyzed and information on a chosen model working activity with high work efficiency.

Provided are moving image obtaining means that obtains a moving image of a region including at least a mouth or a peripheral portion of the mouth in a face, analysis means that analyzes a chewing action based on the moving image of the region obtained by the moving image obtaining means, quality determination means that determines quality of the chewing action based on information of the chewing action analyzed by the analysis means, and extraction means that extracts assistance information corresponding to the chewing quality determined by the quality determination means, from chewing information storage means.

Provided are moving image obtaining means that obtains a moving image of a region including at least a mouth or a peripheral portion of the mouth in a face, analysis means that analyzes a chewing action based on the moving image of the region obtained by the moving image obtaining means, quality determination means that determines quality of the chewing action based on information of the chewing action analyzed by the analysis means, and extraction means that extracts assistance information corresponding to the chewing quality determined by the quality determination means, from chewing information storage means.

An information processor according to the present technology includes a presentation processing section configured to perform a process to present a list of objects recognized in an object recognition process of a captured image to a user, and a tracking processing section configured to set a tracking range of a subject corresponding to an object selected by the user from the list presented by the presentation processing section and perform a tracking process of the subject on the basis of the set tracking range.

A behavior recognition method and system, including: dividing video data into a plurality of video clips, performing frame extraction processing on each video clip to obtain frame images, and performing optical flow extraction on the frame images to obtain optical flow images; performing feature extraction on the frame images and the optical flow images to obtain feature maps of the frame images and the optical flow images; performing spatio-temporal convolution processing on the feature maps of the frame images and the optical flow images, and determining a spatial prediction result and a temporal prediction result; fusing the spatial prediction results of all the video clips to obtain a spatial fusion result, and fusing the temporal prediction results of all the video clips to obtain a temporal fusion result; and performing two-stream fusion on the spatial fusion result and the temporal fusion result to obtain a behavior recognition result.

A method of processing an image, an electronic device, and a storage medium, which relate to the artificial intelligence field, in particular to fields of computer vision and intelligent transportation technologies. The method includes: determining at least one key frame image in a scene image sequence captured by a target camera; determining a camera pose parameter associated with each key frame image in the at least one key frame image, according to a geographic feature associated with the key frame image; and projecting each scene image in the scene image sequence to obtain a target projection image according to the camera pose parameter associated with the key frame image, so as to generate a scene map based on the target projection image. The geographic feature associated with any key frame image indicates localization information of the target camera at a time instant of capturing the corresponding key frame image.

A method and a device for multi-object tracking, and an electronic device are provided. The method includes: determining a hybrid-time position map of a current point cloud fragment; converting a tracked position map of a previous point cloud fragment into a temporary tracked position map of the current point cloud fragment; and averaging the hybrid-time position map and the temporary tracked position map of the current point cloud fragment, to generate a tracked position map of the current point cloud fragment. With the method and the device for multi-object tracking, and the electronic device, the hybrid-time position map and temporary tracked position map of the current point cloud fragment are averaged, so that not only the tracked position map of the current point cloud fragment is accurately generated, but also an object ID is inherited. Based on the object ID, the same object in different point cloud fragments are associated, so that multi-object tracking is implemented without an association step in the conventional solutions. It is unnecessary to set additional hyper-parameters, and strong versatility is achieved.

A tracking method, for tracking an object based on a computer vision, includes following steps. A series of images is captured by a tracking camera. A first position of a trackable device is tracked within the images. An object is recognized around the first position in the images. In response to the object being recognized, a second position of the object is tracked in the images.

A tracking method, for tracking an object based on a computer vision, includes following steps. A series of images is captured by a tracking camera. A first position of a trackable device is tracked within the images. An object is recognized around the first position in the images. In response to the object being recognized, a second position of the object is tracked in the images.