An object tracking method and an object tracking apparatus, which are adapted for a low latency application, are provided. In the method, an object detection is performed on one of continuous image frames. The objection detection is configured to identify a target. The continuous image frames are temporarily stored. An objection tracking is performed on the temporarily stored continuous image frames according to a result of the object detection. The objection tracking is configured to associate the target in one of the continuous image frames with the target in another of the continuous image frames. Accordingly, the accuracy of object tracking may be improved, and the requirement for low latency may be satisfied.

An action recognition method and apparatus related to artificial intelligence and include extracting a spatial feature of a to-be-processed picture, determining a virtual optical flow feature of the to-be-processed picture based on the spatial feature and X spatial features and X optical flow features in a preset feature library, where the X spatial features and the X optical flow features include a one-to-one correspondence, determining a first type of confidence of the to-be-processed picture in different action categories based on similarities between the virtual optical flow feature and Y optical flow features, where each of the Y optical flow features in the preset feature library corresponds to one action category, X and Y are both integers greater than 1, and determining an action category of the to-be-processed picture based on the first type of confidence.

An action recognition method and apparatus related to artificial intelligence and include extracting a spatial feature of a to-be-processed picture, determining a virtual optical flow feature of the to-be-processed picture based on the spatial feature and X spatial features and X optical flow features in a preset feature library, where the X spatial features and the X optical flow features include a one-to-one correspondence, determining a first type of confidence of the to-be-processed picture in different action categories based on similarities between the virtual optical flow feature and Y optical flow features, where each of the Y optical flow features in the preset feature library corresponds to one action category, X and Y are both integers greater than 1, and determining an action category of the to-be-processed picture based on the first type of confidence.

This application disclose a method for training a model performed at a computing device. The method includes: acquiring a template image and a test image; invoking a first object recognition model to process a feature of a tracked object in the template image to obtain a first reference response, and a second object recognition model to process the feature in the template image to obtain a second reference response; invoking the first model to process a feature of a tracked object in the test image to obtain a first test response, and the second model to process the feature to obtain a second test response; tracking the first test response to obtain a tracking response of the tracked object; and updating the first object recognition model based on differences between the first and second reference responses, that between the first and second test responses, and that between a tracking label and the tracking response.

This application disclose a method for training a model performed at a computing device. The method includes: acquiring a template image and a test image; invoking a first object recognition model to process a feature of a tracked object in the template image to obtain a first reference response, and a second object recognition model to process the feature in the template image to obtain a second reference response; invoking the first model to process a feature of a tracked object in the test image to obtain a first test response, and the second model to process the feature to obtain a second test response; tracking the first test response to obtain a tracking response of the tracked object; and updating the first object recognition model based on differences between the first and second reference responses, that between the first and second test responses, and that between a tracking label and the tracking response.

An X-ray imaging system using multiple puked X-ray sources to perform highly efficient and ultrafast 3D radiography is presented. There are multiple puked X-ray sources mounted on a structure in motion to form an array of sources. The multiple X-ray sources move simultaneously relative to an object on a pre-defined arc track at a constant speed as a group. Electron beam inside each individual X-ray tube is deflected by magnetic or electrical field to move focal spot a small distance. When focal spot of an X-ray tube beam has a speed that is equal to group speed but with opposite moving direction, the X-ray source and X-ray flat panel detector are activated through an external exposure control unit so that source tube stay momentarily standstill equivalently. 3D scan can cover much wider sweep angle in much shorter time and image analysis can also be done in real-time.

The present disclosure relates to image processing. The method includes acquiring at least one of a backward propagation feature of an (x+1)th video frame in a video segment or a forward propagation feature of an (x−1)th video frame in the video segment. The video segment includes N video frames, N being an integer greater than 2, and x being an integer. The method further includes deriving a reconstruction feature of the xth video frame from at least one of the xth video frame, the backward propagation feature of the (x+1)th video frame, or the forward propagation feature of the (x−1)th video frame, and deriving a target video frame corresponding to the xth video frame by reconstructing the xth video frame based on the reconstruction feature of the xth video frame. The target video frame has resolution higher than that of the xth video frame.

The present disclosure relates to image processing. The method includes acquiring at least one of a backward propagation feature of an (x+1)th video frame in a video segment or a forward propagation feature of an (x−1)th video frame in the video segment. The video segment includes N video frames, N being an integer greater than 2, and x being an integer. The method further includes deriving a reconstruction feature of the xth video frame from at least one of the xth video frame, the backward propagation feature of the (x+1)th video frame, or the forward propagation feature of the (x−1)th video frame, and deriving a target video frame corresponding to the xth video frame by reconstructing the xth video frame based on the reconstruction feature of the xth video frame. The target video frame has resolution higher than that of the xth video frame.

The present disclosure discloses a microwave identification method, which is implemented on at least one device, including at least one processor and at least one storage device, the method including: the at least one processor obtains microwave data; the at least one processor generates an image of one or more objects based on the microwave data; the at least one processor obtains a model of each of the one or more objects; and based on the model of each of the one or more objects, the at least one processor identifies the one or more objects in the image of the one or more objects.

An information processing apparatus creates a dated image data list by classifying a plurality of dated image data, associates the dated image data list with a specific user, acquires the dated image data for a subject, which is similar to a subject of dateless image data, from the dated image data list, and derives a date to be added to the dateless image data, based on the date added to the acquired dated image data. The plurality of dated image data are image data of a plurality of users including the specific user. The dated image data list is created by classifying the plurality of dated image data for each subject. The dated image data list for a subject, which is similar to a subject of the dated image data, is associated with the specific user.