使用Defilters克服野外目标检测中的场景上下文约束
Overcoming Scene Context Constraints for Object Detection in wild using Defilters
AI总结:
针对野外非受控环境下图像失真影响目标检测性能的问题,提出在检测前用图像defilter校正失真的新方法,在验证集和测试集上分别提升0.562和0.564的平均精度均值,为相关实际应用提供助力。
摘要:
本文聚焦于通过解决非受控采集环境中常见的图像失真问题,提升目标检测性能。目标检测、识别、分割等高层计算机视觉任务对图像失真尤为敏感。为解决该问题,我们提出一种新方法,采用图像defilter(去滤镜)模块在目标检测前校正图像失真。由于模型在非失真图像上训练时性能最优,该方法可提升目标检测准确率。我们的实验表明,与在失真图像上训练目标检测模型相比,使用经defilter处理的图像可显著提升平均精度均值。因此,该方法对受图像失真困扰的实际应用具有显著价值。据我们所知,本研究的贡献在于将失真去除范式应用于自然场景下拍摄图像的目标检测,我们在验证集和测试集上分别实现了0.562和0.564的平均精度均值提升。
英文摘要:
This paper focuses on improving object detection performance by addressing the issue of image distortions, commonly encountered in uncontrolled acquisition environments. High-level computer vision tasks such as object detection, recognition, and segmentation are particularly sensitive to image distortion. To address this issue, we propose a novel approach employing an image defilter to rectify image distortion prior to object detection. This method enhances object detection accuracy, as models perform optimally when trained on non-distorted images. Our experiments demonstrate that utilizing defiltered images significantly improves mean average precision compared to training object detection models on distorted images. Consequently, our proposed method offers considerable benefits for real-world applications plagued by image distortion. To our knowledge, the contribution lies in employing distortion-removal paradigm for object detection on images captured in natural settings. We achieved an improvement of 0.562 and 0.564 of mean Average precision on validation and test data.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。