Method for constructing spectral image detection model, detection method, and camera processor capable of on-chip computing

By constructing an ultra-lightweight spectral image detection model based on an attention mechanism and an on-chip computing camera processor, the problems of computational and storage-intensive hyperspectral image detection models are solved, enabling efficient detection and real-time applications on a camera processor, suitable for mobile and edge devices.

WO2026113840A1PCT designated stage Publication Date: 2026-06-04HUNAN UNIV
View PDF 7 Cites 0 Cited by

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
HUNAN UNIV
Filing Date
2025-10-31
Publication Date
2026-06-04

AI Technical Summary

Technical Problem

Existing hyperspectral image detection network models are complex and computationally intensive, resulting in high computational and storage requirements. This makes them difficult to deploy on ordinary industrial cameras. Furthermore, the large size of hyperspectral images makes it difficult to achieve real-time applications at edge devices and on mobile devices.

Method used

An ultra-lightweight spectral image detection model based on an attention mechanism is constructed, including N cascaded KAM blocks and a classifier block. Depth-separable convolutional layers, improved triple attention layers, and ReLU activation function layers are used to reduce computation and storage requirements. The spectral image detection model is deployed in an on-chip computing camera processor, and image acquisition, preprocessing, and detection are realized using an FPGA processor.

Benefits of technology

It enables efficient hyperspectral image detection on camera processors, reduces computing and storage requirements, supports real-time applications on mobile and edge devices, and features miniaturization and low power consumption.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2025131789_04062026_PF_FP_ABST
    Figure CN2025131789_04062026_PF_FP_ABST
Patent Text Reader

Abstract

A spectral image detection model, a detection method, and a camera processor capable of on-chip computing. The spectral image detection model comprises N KAM blocks connected in series and a classifier block connected after the N KAM blocks; each KAM block comprises a depthwise separable convolution layer, a batch normalization layer, an improved triple attention layer, and a ReLU activation function layer which are connected in sequence; the depthwise separable convolution layer is used for extracting image features; the improved triple attention layer is used for enhancing information interaction within and between feature maps; and the classifier block comprises a depthwise separable convolution layer, a batch normalization layer, an ordinary convolution layer, and a Sigmoid activation function layer which are connected in sequence. The spectral image detection model has the characteristics of light weight, low computational complexity, etc. and can be deployed in a camera processor in a camera, so as to meet the requirements for hyperspectral image processing at mobile devices and edge devices.
Need to check novelty before this filing date? Find Prior Art