Abstract: Provided herein is a method, apparatus, and computer program product for classifying objects as static objects or dynamic objects based on point cloud data. Methods may include: receiving point cloud data representative of an environment; computing voxel sequences from the point cloud data; extracting voxel-wise semantic features from the voxel sequences; modeling voxel-wise temporal changes based on the voxel-wise semantic features; and classifying objects in the environment as dynamic objects or static objects based on the modeled voxel-wise temporal changes. Computing voxel sequences from the point cloud data may include using a voxel cloud connectivity segmentation method to group voxels in point clouds into perceptually meaningful regions.

Abstract: A computer-implemented method of detecting a foreign object on a background object in an image is provided. The computer-implemented method includes extracting image features of the image based on image characteristics of the background object and a suspected foreign object; detecting a salient region in the image based on a human visual attention model; generating a salient region mask based on detection of the salient region; obtaining the image features in a region surrounded by the salient region mask; perforating feature combination and feature vector length normalization on the image features of the region surrounded by the salient region mask to generate normalized feature vectors; and identifying the suspected foreign object using an image classifier, wherein the image classifier uses the normalized feature vectors as input for identifying the suspected foreign object.

Abstract: A sample extraction method targeting a video classification problem includes acquiring video data, parsing the video data to obtain a plurality of consecutive single-frame images corresponding to the video data, and extracting feature images from the plurality of consecutive single-frame images to compose samples, where the feature images are used to summarize content information of the video data, and the samples do not contain redundant image data.

Abstract: The present disclosure proposes an end-to-end text recognition method and apparatus, computer device and readable medium. The method comprises: obtaining a to-be-recognized picture containing a text region; recognizing a position of the text region in the to-be-recognized picture and text content included in the text region with a pre-trained end-to-end text recognition model; the end-to-end text recognition model comprising a region of interest perspective transformation processing module for performing perspective transformation processing for the text region. The technical solution of the present disclosure does not need to serially arrange a plurality of steps, and may avoid introducing the accumulated errors and may effectively improve the accuracy of the text recognition.

Abstract: Systems and processes for analyzing an image. Analyzing the image may comprise selecting a computer vision parameter for an image feature identification process. The image feature identification process may identify at least one feature in the image when using the computer vision parameter. Analyzing the image may further comprise segmenting the image into a region of interest T and a background region B. Analyzing the image may further comprise calculating a set of statistical values about the region of interest T of the image. Analyzing the image may further comprise classifying the image based on both the computer vision parameter and the set of statistical values as one of either: a defect containing image or a defect free image.