A video processing apparatus configured to process a stream of video surveillance data, wherein the video surveillance data includes metadata associated with video data, the metadata describing at least one object in the video data. The apparatus comprises means for applying an image assessment algorithm to generate a reliability score for the metadata, and associating the reliability score with the metadata. The image assessment algorithm generates the reliability score based on an assessment of the image quality of the video data to which the metadata relates to indicate a likelihood that the metadata accurately describes the object. An image enhancement module applies image enhancement to video data if the reliability score of metadata associated with the video data indicates a low likelihood that the metadata accurately describes the object.

A processor-implemented method of generating feature data includes: receiving an input image; generating, based on a pixel value of the input image, at least one low-bit image having a number of bits per pixel lower than a number of bits per pixel of the input image; and generating, using at least one neural network, feature data corresponding to the input image from the at least one low-bit image.

A method and an apparatus for recognizing an object are disclosed. The apparatus may extract a plurality of features from an input image using a single recognition model and recognize an object in the input image based on the extracted features. The single recognition model may include at least one compression layer configured to compress input information and at least one decompression layer configured to decompress the compressed information to determine the features.

A target tracking method and apparatus is provided. The target tracking apparatus includes a memory configured to store a neural network, and a processor configured to extract feature information of each of a target included in a target region in a first input image, a background included in the target region, and a searching region in a second input image, using the neural network, obtain similarity information of the target and the searching region and similarity information of the background and the searching region based on the extracted feature information, obtain a score matrix including activated feature values based on the obtained similarity information, and estimate a position of the target in the searching region from the score matrix.

A monolithic integrated circuit (IC) including one or more compute circuitry, one or more non-volatile memory circuits, one or more communication channels and one or more communication interface. The one or more communication channels can communicatively couple the one or more compute circuitry, the one or more non-volatile memory circuits and the one or more communication interface together. The one or more communication interfaces can communicatively couple one or more circuits of the monolithic integrated circuit to one or more circuits external to the monolithic integrated circuit.

Systems and methods for obtaining attention features are described. Some examples may include: receiving, at a projector of a transformer, a plurality of tokens associated with image features of a first dimensional space; generating, at the projector of the transformer, projected features by concatenating the plurality of tokens with a positional map, the projected features having a second dimensional space that is less than the first dimensional space; receiving, at an encoder of the transformer, the projected features and generating encoded representations of the projected features using self-attention; decoding, at a decoder of the transformer, the encoded representations and obtaining a decoded output; and projecting the decoded output to the first dimensional space and adding the image features of the first dimensional space to obtain attention features associated with the image features.

Systems and methods for searching a search space are disclosed. Some examples may include using a first parallel module including a first plurality of stacked searching blocks and a second plurality of stacked searching blocks to output first feature maps of a first resolution and to output second feature maps of a second resolution. In some examples, a fusion module may include a plurality of searching blocks, where the fusion module is configured to generate multiscale feature maps by fusing one or more feature maps of the first resolution received from the first parallel module with one or more feature maps of the second resolution received from the first parallel module, and wherein the fusion module is configured to output the multiscale feature maps and output third feature maps of a third resolution.

A quantification system (700) is described that includes: at least one input (710) configured to provide two input medical images and two locations of interest in said input medical images that correspond to a same anatomical region; and a mapping circuit (725) configured to compute a direct quantification of change of said input medical images from the at least one input (710).

An artificial potential field path planning method and an apparatus based on obstacle classification solve the problem of path and motion uncertainty in steering a flexible needle in soft tissue. The apparatus includes an image sensing system, a control module, an execution system and an upper PC. Using the apparatus, the method includes: the image sensing system obtains real-time images of the puncture environment, identifies a target and obstacles from the real-time images, classifies the obstacles, and calculates total potential energy of points in the current environment based on artificial potential field. With a curvature constraint and an optimization index for the flexible needle, the path planning module carries out static path planning to obtain an initial path and the needle entry point, then conducts dynamic path planning to determine the path for steering the flexible needle in the soft tissue accordingly.

System and method for simultaneous object detection and semantic segmentation. The system includes a computing device. The computing device has a processor and a non-volatile memory storing computer executable code. The computer executable code, when executed at the processor, is configured to: receive an image of a scene; process the image using a neural network backbone to obtain a feature map; process the feature map using an object detection module to obtain object detection result of the image; and process the feature map using a semantic segmentation module to obtain semantic segmentation result of the image. The object detection module and the semantic segmentation module are trained using a same loss function comprising an object detection component and a semantic segmentation component.