An image processing method includes: obtaining a first categorical feature and M first image features corresponding to M first images respectively, each first image being associated with a task index, task indices associated with different first images being different from each other, M being a positive integer; fusing the M first image features with the first categorical feature respectively so as to obtain M first target features; performing feature extraction on the M first target features so as to obtain M second categorical features; selecting a second categorical feature corresponding to each task index from the M second categorical features, and performing regularization corresponding to the task index on the second categorical feature, to obtain a third categorical feature corresponding to the task index; and performing image processing in accordance with M third categorical features so as to obtain M first image processing results of the M first images.

An image processing method includes: obtaining a first categorical feature and M first image features corresponding to M first images respectively, each first image being associated with a task index, task indices associated with different first images being different from each other, M being a positive integer; fusing the M first image features with the first categorical feature respectively so as to obtain M first target features; performing feature extraction on the M first target features so as to obtain M second categorical features; selecting a second categorical feature corresponding to each task index from the M second categorical features, and performing regularization corresponding to the task index on the second categorical feature, to obtain a third categorical feature corresponding to the task index; and performing image processing in accordance with M third categorical features so as to obtain M first image processing results of the M first images.

A method for training a homography attention module (HAM) to perform multi-view object detection includes steps of: generating, from an i-th feature map corresponding to each of multiple training images representing multi-views of a target space, a 1-st to a d-th channel attention map for determining channel attention scores each channel included in the i-th feature map has for each of a 1-st to a d-th height plane of the target space, generating a 1-st to a d-th channel refined feature map by referring to channels with top k channel attention scores for each height, element-wisely multiplying them with corresponding spatial attention map generated therefrom to produce a 1-st to a d-th spatial refined feature map, and then homographically transforming them onto corresponding height plane and aggregating them to generate a BEV occupancy heatmap, which is used with its GT for training.

A method for training a homography attention module (HAM) to perform multi-view object detection includes steps of: generating, from an i-th feature map corresponding to each of multiple training images representing multi-views of a target space, a 1-st to a d-th channel attention map for determining channel attention scores each channel included in the i-th feature map has for each of a 1-st to a d-th height plane of the target space, generating a 1-st to a d-th channel refined feature map by referring to channels with top k channel attention scores for each height, element-wisely multiplying them with corresponding spatial attention map generated therefrom to produce a 1-st to a d-th spatial refined feature map, and then homographically transforming them onto corresponding height plane and aggregating them to generate a BEV occupancy heatmap, which is used with its GT for training.

An image matting method and apparatus, an electronic device, and a computer-readable storage medium. The method comprises: performing feature point detection on an image so as to obtain a feature point; acquiring a first image region manually marked on the image; adjusting the first image region according to the feature point, so as to obtain a second image region; and performing matting on the image according to the second image region. The manually marked first image region is adjusted according to the feature point, so as to acquire the second image region which is more accurately positioned, and then matting can be performed according to the second image region so as to accurately extract a required region.

An image matting method and apparatus, an electronic device, and a computer-readable storage medium. The method comprises: performing feature point detection on an image so as to obtain a feature point; acquiring a first image region manually marked on the image; adjusting the first image region according to the feature point, so as to obtain a second image region; and performing matting on the image according to the second image region. The manually marked first image region is adjusted according to the feature point, so as to acquire the second image region which is more accurately positioned, and then matting can be performed according to the second image region so as to accurately extract a required region.

The disclosure provides an objective identification device, comprising: a classifier training circuit configured to extract objective characteristics based on training samples and perform offline training based on the objective characteristics to obtain a classifier; and a calculation circuit is configured to identify an objective in an image based on a particle swarm optimization algorithm, wherein each of particles is defined as an object having a predefined size in the image; and a fitness value of each of particles is calculated based on the classifier and the objective characteristics of the particle in the particle swarm optimization algorithm, the fitness value representing a probability that the particle belongs to the objective. The disclosure also provides an objective identification method and driving assistance device. According to the disclosure, not only the identification rate can be increased but also application scenarios having different identification rate requirements can be satisfied.

In the image processing device, the image processing method, the program, and the recording medium according to an embodiment of the present invention, a processor connected to a memory, the processor configured to receive an input of an image set owned by a user, analyze each image included in the image set, determine a plurality of tag information of an imaging content in the image set based on an analyzing result of each image, set one or more objectives to be achieved by the user based on the plurality of tag information, and set one or more items to be executed by the user for each of the one or more objectives based on the analyzing result of each image, and perform control such that at least one of the one or more objectives or the one or more items is displayed on a display.

A system and method for providing object-level driver attention reasoning with a graph convolution network that include receiving image data associated with a plurality of image clips of a surrounding environment of a vehicle and determining anchor object-ness scores and anchor importance scores associated with relevant objects included within the plurality of image clips. The system and method also include analyzing the anchor object-ness scores and anchor importance scores associated with relevant objects and determining top relevant objects with respect to an operation of the vehicle. The system and method further include passing object node features and edges of an interaction graph through the graph convolution network to update features of each object node through interaction with other object nodes and determining importance scores for the top relevant objects.

A classifier network has at least two distinct sets of refined data, wherein the first two sets of refined data are sets of numbers representing the features values data received from sensors or a manufactured part. Performing, via at least two distinct types of support vector machines using an associated feature selection process for each classifier independently in a first layer, anomaly detection on the manufactured part. Then, using the stored data including refined data of at least two different types of data transforms and performing, via at least a two distinct types of support vector machines in a second layer, an associated feature selection process for each classifier independently. Forming at least four distinct compound classifier types for anomaly detection on the part using the stored data or coefficients. The ensemble of second layer support vector machine outputs compare the results to determine the presence of an anomaly.