Abstract: Provided are a method, apparatus and device for extracting image features, and a storage medium. The method includes: obtaining parameters to be quantized of a network layer in a neural network model; determining whether values of the parameters to be quantized are all positive numbers; when the values of the parameters to be quantized are all positive numbers, executing, based on an asymmetric linear quantization logic, a quantization operation on the parameters to be quantized; when the values of the parameters to be quantized are not all positive numbers, executing, based on a symmetric linear quantization logic, a quantization operation on the parameters to be quantized; and extracting features of an input image by using the neural network model for which the quantization operation has been executed.

Abstract: An image registration method and apparatus, an electronic apparatus, and a storage medium are provided. The image registration method comprises: extracting edge pixels of the binocular image, and determining high-confidence parallax points in the edge pixels and parallax; projecting each non-high-confidence parallax point to the triangular mesh in a direction parallel with a parallax dimension to obtain a triangular face; determining a parallax search range of parallax of each non-high-confidence parallax point, calculating a matching cost corresponding to all parallax in each parallax search range, and determining that parallax with the smallest matching cost is the parallax of the corresponding non-high-confidence parallax point; and determining a depth boundary point in the edge pixels, determining a parallax boundary point of each depth boundary point in a target direction, and setting parallax of pixels between the depth boundary point and the parallax boundary point to a target value.

Abstract: Disclosed are a distributed quantum imaging method, apparatus and system, and a computer-readable storage medium. The distributed quantum imaging system comprises a plurality of laser devices that are placed at different spatial positions, a plurality of spatial light modulators, a detector and an imaging processor, wherein each laser device uniquely corresponds to one spatial light modulator.

Abstract: Provided are a method, apparatus and device for extracting image features, and a storage medium. The method includes: obtaining parameters to be quantized of a network layer in a neural network model (S101); determining whether values of the parameters to be quantized are all positive numbers (S102); when the values of the parameters to be quantized are all positive numbers, executing, based on an asymmetric linear quantization logic, a quantization operation on the parameters to be quantized (S103); when the values of the parameters to be quantized are not all positive numbers, executing, based on a symmetric linear quantization logic, a quantization operation on the parameters to be quantized (S104); and extracting features of an input image by using the neural network model for which the quantization operation has been executed (S105).

Abstract: An image registration method and apparatus, an electronic apparatus, and a storage medium are provided. The image registration method comprises: extracting edge pixels of the binocular image, and determining high-confidence parallax points in the edge pixels and parallax; projecting each non-high-confidence parallax point to the triangular mesh in a direction parallel with a parallax dimension to obtain a triangular face; determining a parallax search range of parallax of each non-high-confidence parallax point, calculating a matching cost corresponding to all parallax in each parallax search range, and determining that parallax with the smallest matching cost is the parallax of the corresponding non-high-confidence parallax point; and determining a depth boundary point in the edge pixels, determining a parallax boundary point of each depth boundary point in a target direction, and setting parallax of pixels between the depth boundary point and the parallax boundary point to a target value.

Abstract: Provided are a sequence alignment method and system. The method comprises: searching for candidate alignment locations of all seeds in a sequence to be aligned, and after performing normalization processing on the candidate alignment locations of all seeds, acquiring the longest seeds of various types in a bitmap mode; and then filtering out all seeds covered by the longest seeds, so that the number of candidate comparison locations needing to be aligned subsequently is reduced. Therefore, the workload of subsequent alignment work is greatly reduced, the sequence alignment speed is increased, and meanwhile, the alignment precision is guaranteed.

Abstract: A filter processing method for a sequence alignment is provided. The method includes: searching for absolute locations of all seeds of a to-be-aligned sequence in a reference sequence; performing segmentation on the absolute locations of the seeds to obtain relative locations of the seeds; dividing the reference sequence into multiple reference sub-sequences and establishing a mapping relationship between a relative location of each seed and a corresponding reference sub-sequence; determining a reference sub-sequence to which each seed belongs and counting the occurrence numbers of the seeds in each reference sub-sequence; filtering out a reference sub-sequence that does not meet a preset condition to obtain a target reference sub-sequence; and recovering a real CAL based on a difference between a relative location and an absolute location of each seed in the target reference sub-sequence.