Saved in:
Bibliographic Details
Main Authors: Li, Zhaoxu, An, Wei, Guo, Gaowei, Wang, Longguang, Wang, Yingqian, Lin, Zaiping
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.10148
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911364458479616
author Li, Zhaoxu
An, Wei
Guo, Gaowei
Wang, Longguang
Wang, Yingqian
Lin, Zaiping
author_facet Li, Zhaoxu
An, Wei
Guo, Gaowei
Wang, Longguang
Wang, Yingqian
Lin, Zaiping
contents Hyperspectral target detection (HTD) aims to identify specific materials based on spectral information in hyperspectral imagery and can detect extremely small-sized objects, some of which occupy a smaller than one-pixel area. However, existing HTD methods are developed based on per-pixel binary classification, neglecting the three-dimensional cube structure of hyperspectral images (HSIs) that integrates both spatial and spectral dimensions. The synergistic existence of spatial and spectral features in HSIs enable objects to simultaneously exhibit both, yet the per-pixel HTD framework limits the joint expression of these features. In this paper, we rethink HTD from the perspective of spatial-spectral synergistic representation and propose hyperspectral point object detection as an innovative task framework. We introduce SpecDETR, the first specialized network for hyperspectral multi-class point object detection, which eliminates dependence on pre-trained backbone networks commonly required by vision-based object detectors. SpecDETR uses a multi-layer Transformer encoder with self-excited subpixel-scale attention modules to directly extract deep spatial-spectral joint features from hyperspectral cubes. We develop a simulated hyperspectral point object detection benchmark termed SPOD, and for the first time, evaluate and compare the performance of visual object detection networks and HTD methods on hyperspectral point object detection. Extensive experiments demonstrate that our proposed SpecDETR outperforms SOTA visual object detection networks and HTD methods. Our code and dataset are available at https://github.com/ZhaoxuLi123/SpecDETR.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10148
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SpecDETR: A transformer-based hyperspectral point object detection network
Li, Zhaoxu
An, Wei
Guo, Gaowei
Wang, Longguang
Wang, Yingqian
Lin, Zaiping
Computer Vision and Pattern Recognition
Hyperspectral target detection (HTD) aims to identify specific materials based on spectral information in hyperspectral imagery and can detect extremely small-sized objects, some of which occupy a smaller than one-pixel area. However, existing HTD methods are developed based on per-pixel binary classification, neglecting the three-dimensional cube structure of hyperspectral images (HSIs) that integrates both spatial and spectral dimensions. The synergistic existence of spatial and spectral features in HSIs enable objects to simultaneously exhibit both, yet the per-pixel HTD framework limits the joint expression of these features. In this paper, we rethink HTD from the perspective of spatial-spectral synergistic representation and propose hyperspectral point object detection as an innovative task framework. We introduce SpecDETR, the first specialized network for hyperspectral multi-class point object detection, which eliminates dependence on pre-trained backbone networks commonly required by vision-based object detectors. SpecDETR uses a multi-layer Transformer encoder with self-excited subpixel-scale attention modules to directly extract deep spatial-spectral joint features from hyperspectral cubes. We develop a simulated hyperspectral point object detection benchmark termed SPOD, and for the first time, evaluate and compare the performance of visual object detection networks and HTD methods on hyperspectral point object detection. Extensive experiments demonstrate that our proposed SpecDETR outperforms SOTA visual object detection networks and HTD methods. Our code and dataset are available at https://github.com/ZhaoxuLi123/SpecDETR.
title SpecDETR: A transformer-based hyperspectral point object detection network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.10148