Image cross-modal saliency detection method and device, equipment and medium

CN121437852APending Publication Date: 2026-01-30BEIHANG UNIV
View PDF -1 Cites 0 Cited by

Patent Information

Application Number
CN202511584168.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-10-31
Publication Date
2026-01-30

AI Technical Summary

Technical Problem

Existing neural network-based salient object detection methods have low accuracy and lack interpretability, making it difficult to meet the high-level semantic and abstract knowledge requirements in multimodal image processing.

Method used

By acquiring color and depth images, a first phase map and a second phase map are determined respectively. The saliency phase map is iteratively updated using a phase update and transformation model. Combined with the conversion between the frequency domain and the spatial domain, a saliency map is generated.

Benefits of technology

It achieves cross-modal saliency detection with high accuracy and interpretability, and can effectively utilize information from both color and depth modalities to generate saliency maps that conform to human visual attention mechanisms.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121437852A_ABST
    Figure CN121437852A_ABST
Patent Text Reader

Abstract

The embodiment of the invention relates to an image cross-modal saliency detection method and device, equipment and a medium. The method comprises the steps that a color image and a depth image corresponding to the color image are acquired; determining a first phase diagram corresponding to the color image, and determining a second phase diagram corresponding to the depth image; performing saliency phase updating processing based on preset distribution according to the color image, the depth image, the first phase diagram and the second phase diagram to obtain a saliency phase diagram; and according to the color image and the depth image, carrying out conversion from a frequency domain to a space domain on the saliency phase diagram to obtain a saliency map. According to the embodiment of the invention, on the basis that the discovered color image and the depth image have phase consistency of frequency spectrums with the saliency map, that is, the phase-related data obeys the preset distribution, the two modes of color and depth are taken as input, the saliency map is taken as output, and three different image modes are involved; and cross-modal saliency target detection with interpretability and relatively high accuracy is realized.
Need to check novelty before this filing date? Find Prior Art