用合成数据和新模型提升雾霾野生动物图像质量，助力保护工作。
Enhancing Hazy Wildlife Imagery: AnimalHaze3k and IncepDehazeGan
- 用物理方法生成3477张雾霾野生动物图，构建AnimalHaze3k数据集。
- 新模型IncepDehazeGan在去雾指标上超越现有方法，SSIM提升6.27%。
- 去雾后图像让目标检测性能提升112%，适合生态监测应用。
大气雾霾严重降低野生动物图像质量，影响动物检测、追踪与行为分析等保护性计算机视觉任务。为此，我们提出AnimalHaze3k合成数据集，包含3,477张由1,159张清晰野生动物图像通过物理模型生成的雾霾图像。提出的IncepDehazeGan架构在生成对抗网络中融合膨胀块与残差跳跃连接，在去雾性能上达到最优（SSIM: 0.8914，PSNR: 20.54，LPIPS: 0.1104），相较现有方法提升6.27%的SSIM和10.2%的PSNR。应用于下游检测任务时，去雾图像使YOLOv11的mAP提升112%，IoU提升67%。该成果为生态学家在恶劣环境下的种群监测与巡护提供了可靠视觉分析工具，显著推动野生动物保护中的视觉技术应用。
原文摘要 · Abstract (English)
Atmospheric haze significantly degrades wildlife imagery, impeding computer vision applications critical for conservation, such as animal detection, tracking, and behavior analysis. To address this challenge, we introduce AnimalHaze3k a synthetic dataset comprising of 3,477 hazy images generated from 1,159 clear wildlife photographs through a physics-based pipeline. Our novel IncepDehazeGan architecture combines inception blocks with residual skip connections in a GAN framework, achieving state-of-the-art performance (SSIM: 0.8914, PSNR: 20.54, and LPIPS: 0.1104), delivering 6.27% higher SSIM and 10.2% better PSNR than competing approaches. When applied to downstream detection tasks, dehazed images improved YOLOv11 detection mAP by 112% and IoU by 67%. These advances can provide ecologists with reliable tools for population monitoring and surveillance in challenging environmental conditions, demonstrating significant potential for enhancing wildlife conservation efforts through robust visual analytics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。