计算机科学与探索

• 学术研究 •    

基于深度学习的伪装目标检测综述

史彩娟, 任弼娟, 王子雯, 闫巾玮, 石泽   

  1. 1.华北理工大学 人工智能学院,河北 唐山 063210
    2.河北省工业智能感知重点实验室, 河北 唐山 063210

A Survey of Camouflaged Object Detection Based on Deep Learning

SHI Caijuan, REN Bijuan, WANG Ziwen, YAN Jinwei, SHI Ze   

  1. 1.College of Artificial Intelligence, North China University of Science and Technology, Tangshan, Hebei 063210, China
    2.Hebei Key Laboratory of Industrial Intelligent Perception, Tangshan, Hebei 063210, China

摘要: 基于深度学习的伪装目标检测是一项新兴的视觉检测任务,其目的是精确且高效地检测出“完美”嵌入周围环境中的伪装目标。目前大多数工作旨在构建不同的伪装目标检测模型,对现有模型的归纳总结及深入分析的综述性工作还很少。因此,对基于深度学习的伪装目标检测模型进行了全面分析和总结,并探讨了伪装目标检测未来的研究方向。首先对基于深度学习的23个伪装目标检测模型分别从由粗到细策略、多任务学习策略、置信感知学习策略、多源信息融合策略以及基于Transformer五个角度进行了分类介绍,并对每种策略的优劣进行了深入分析;其次介绍了伪装目标检测广泛使用的4个数据集以及4种评估准则;然后对现有基于深度学习的伪装目标检测模型在4个数据集上进行了性能比较,包括定量比较、视觉比较和效率分析,并分析了这些模型对不同类型目标的检测效果;接着简单介绍了伪装目标检测在医学、工业、农业、军事、艺术等领域的应用;最后指出了现有方法在复杂场景、多尺度目标、实时性、实际应用需求、多模态等方面存在的不足和挑战,并探讨了伪装目标检测未来的研究方向。

关键词: 伪装目标检测, 深度学习, 性能比较

Abstract: Camouflaged object detection (COD) based on deep learning is an emerging visual detection task, which aims to detect the camouflaged objects "perfectly" embedded in the surrounding environment. However, most exiting works primarily focus on building different COD models with little summary work for the existing methods. Therefore, our paper summarizes the existing COD methods based on deep learning and discusses the future development of COD. Firstly, the 23 exiting COD models based on deep learning are introduced and analyzed according to five detection mechanisms: coarse-to-fine strategy, multi-task learning strategy, confidence-aware learning strategy, multi source information fusion strategy and transformer-based strategy. And then, the 4 widely used datasets and 4 evaluation metrics for COD are introduced. In addition, the performance of the existing COD models based on deep learning are compared on four datasets, including quantitative comparison, visual comparison, efficiency analysis, and the detection effects on camouflaged objects of different types. Furthermore, the practical applications of COD in the medicine, industry, agriculture, military, art, etc. are mentioned. Finally, the deficiencies and challenges of existing methods in complex scenes, multi-scale objects, real-time performance, practical application requirements, and multimodality COD are pointed out, and the potential directions of COD are discussed.

Key words: camouflaged object detection, deep learning, performance comparison