大多数行人重识别(Person re-identification,ReID)方法仅将注意力机制作为提取显著特征的辅助手段,缺少网络对行人图像关注程度的量化研究.基于此,提出一种可解释注意力部件模型(Interpretable attention part model,IAPM).该模型有3...大多数行人重识别(Person re-identification,ReID)方法仅将注意力机制作为提取显著特征的辅助手段,缺少网络对行人图像关注程度的量化研究.基于此,提出一种可解释注意力部件模型(Interpretable attention part model,IAPM).该模型有3个优点:1)利用注意力掩码提取部件特征,解决部件不对齐问题;2)为了根据部件的显著性程度生成可解释权重,设计可解释权重生成模块(Interpretable weight generation module,IWM);3)提出显著部件三元损失(Salient part triplet loss,SPTL)用于IWM的训练,提高识别精度和可解释性.在3个主流数据集上进行实验,验证所提出的方法优于现有行人重识别方法.最后通过一项人群主观测评比较IWM生成可解释权重的相对大小与人类直观判断得分,证明本方法具有良好的可解释性.展开更多
针对采集图像中铁路扣件存在形状的变化、扣件图像的光照差异较大和扣件被异物局部遮挡的问题,根据对可变形部件模型算法和高斯混合模型的研究,提出了高斯混合部件模型算法.结合扣件图像边缘特性及改进的 Roberts 算子计算图像梯度,将...针对采集图像中铁路扣件存在形状的变化、扣件图像的光照差异较大和扣件被异物局部遮挡的问题,根据对可变形部件模型算法和高斯混合模型的研究,提出了高斯混合部件模型算法.结合扣件图像边缘特性及改进的 Roberts 算子计算图像梯度,将归一化后的方向梯度直方图特征作为高斯混合部件模型算法的底层特征,根据扣件形状划分部件,部件之间的相对位置采用星型连接方式度量,运用余弦相似性度量部件中方向梯度直方图特征的相似度,部件模型使用高斯混合模型并采用期望最大化算法迭代求解.将高斯混合部件模型算法应用于扣件检测中,最终平均检测效果为漏检率 3.16%、误检率 9.80%、正确率 90.27%.展开更多
Person re-IDentification(re-ID) is an important research topic in the computer vision community, with significance for a range of applications. Pedestrians are well-structured objects that can be partitioned, although...Person re-IDentification(re-ID) is an important research topic in the computer vision community, with significance for a range of applications. Pedestrians are well-structured objects that can be partitioned, although detection errors cause slightly misaligned bounding boxes, which lead to mismatches. In this paper, we study the person re-identification performance of using variously designed pedestrian parts instead of the horizontal partitioning routine typically applied in previous hand-crafted part works, and thereby obtain more effective feature descriptors. Specifically, we benchmark the accuracy of individual part matching with discriminatively trained Convolutional Neural Network(CNN) descriptors on the Market-1501 dataset. We also investigate the complementarity among different parts using combination and ablation studies, and provide novel insights into this issue. Compared with the state-of-the-art, our method yields a competitive accuracy rate when the best part combination is used on two large-scale datasets(Market-1501 and CUHK03) and one small-scale dataset(VIPeR).展开更多
This paper presents a novel formulation for detecting objects with articulated rigid bodies from highresolution monitoring images, particularly engineering vehicles. There are many pixels in high-resolution monitoring...This paper presents a novel formulation for detecting objects with articulated rigid bodies from highresolution monitoring images, particularly engineering vehicles. There are many pixels in high-resolution monitoring images, and most of them represent the background. Our method first detects ob ject patches from monitoring images using a coarse detection process. In this phase, we build a descriptor based on histograms of oriented gradient, which contain color frequency information. Then we use a linear support vector machine to rapidly detect many image patches that may contain ob ject parts, with a low false negative rate and a high false positive rate. In the second phase, we apply a refinement classification to determine the patches that actually contain ob jects. In this stage, we increase the size of the image patches so that they include the complete ob ject using models of the ob ject parts.Then an accelerated and improved salient mask is used to improve the performance of the dense scale-invariant feature transform descriptor. The detection process returns the absolute position of positive ob jects in the original images. We have applied our methods to three datasets to demonstrate their effectiveness.展开更多
基金supported by the National Natural Science Foundation of China (Nos. 61771288 and 61701277)the State Key Development Program of the 13th FiveYear Plan (No. 2017YFC0821601)
文摘Person re-IDentification(re-ID) is an important research topic in the computer vision community, with significance for a range of applications. Pedestrians are well-structured objects that can be partitioned, although detection errors cause slightly misaligned bounding boxes, which lead to mismatches. In this paper, we study the person re-identification performance of using variously designed pedestrian parts instead of the horizontal partitioning routine typically applied in previous hand-crafted part works, and thereby obtain more effective feature descriptors. Specifically, we benchmark the accuracy of individual part matching with discriminatively trained Convolutional Neural Network(CNN) descriptors on the Market-1501 dataset. We also investigate the complementarity among different parts using combination and ablation studies, and provide novel insights into this issue. Compared with the state-of-the-art, our method yields a competitive accuracy rate when the best part combination is used on two large-scale datasets(Market-1501 and CUHK03) and one small-scale dataset(VIPeR).
基金supported by the China Knowledge Centre for Engineering Sciences and Technology(No.CKCEST-2014-1-2)the Zhejiang Provincial Natural Science Foundation of China(No.LY14F020027)the National Natural Science Foundation of China(No.61272304)
文摘This paper presents a novel formulation for detecting objects with articulated rigid bodies from highresolution monitoring images, particularly engineering vehicles. There are many pixels in high-resolution monitoring images, and most of them represent the background. Our method first detects ob ject patches from monitoring images using a coarse detection process. In this phase, we build a descriptor based on histograms of oriented gradient, which contain color frequency information. Then we use a linear support vector machine to rapidly detect many image patches that may contain ob ject parts, with a low false negative rate and a high false positive rate. In the second phase, we apply a refinement classification to determine the patches that actually contain ob jects. In this stage, we increase the size of the image patches so that they include the complete ob ject using models of the ob ject parts.Then an accelerated and improved salient mask is used to improve the performance of the dense scale-invariant feature transform descriptor. The detection process returns the absolute position of positive ob jects in the original images. We have applied our methods to three datasets to demonstrate their effectiveness.
