Accurate pedestrian classification and localization have received considerable attention due to their wide applications such as security monitoring, autonomous driving, etc. Although pedestrian detectors have made great progress in recent years, the fixed Intersection over Union (IoU) based assignment-regression manner still limits their performance. Two main factors are responsible for this: 1) the IoU threshold faces a dilemma that a lower one will result in more false positives, while a higher one will filter out the matched positives; 2) the IoU-based GT-Proposal assignment suffers from the inconsistent supervision problem that spatially adjacent proposals with similar features are assigned to different ground-truth boxes, which means some very similar proposals may be forced to regress towards different targets, and thus confuses the bounding-box regression when predicting the location results. In this paper, we first put forward the question that \textbf{Regression Direction} would affect the performance for pedestrian detection. Consequently, we address the weakness of IoU by introducing one geometric sensitive search algorithm as a new assignment and regression metric. Different from the previous IoU-based \textbf{one-to-one} assignment manner of one proposal to one ground-truth box, the proposed method attempts to seek a reasonable matching between the sets of proposals and ground-truth boxes. Specifically, we boost the MR-FPPI under R$_{75}$ by 8.8\% on Citypersons dataset. Furthermore, by incorporating this method as a metric into the state-of-the-art pedestrian detectors, we show a consistent improvement.
翻译:准确的行人分类和本地化由于安全监测、自主驾驶等应用范围很广,因此受到相当的重视。虽然近年来行人探测器取得了很大进展,但基于联合(IoU)的固定交叉路段基于任务回归方式仍然限制其业绩。 造成这种情况的两个主要因素是:(1) IoU门槛面临一个进退两难的难题,即较低的门槛会导致更多的假正数,而更高的门槛将过滤出匹配的正数;(2) 以IoU为基础的GT-Proposal任务存在一个不一致的监督问题,即具有类似特征的空间相邻提案被分配到不同的地盘框,这意味着一些非常相似的提案可能被迫向不同的目标倒退,从而混淆了预测位置结果时的界限框回归。 在本文中,我们首先提出这样的问题,即较低一个较低的进程将影响行人探测的性能。 因此,我们通过引入一个几何测量敏感的搜索算法作为新的任务和回归度衡量标准来解决IoU的弱点。 与先前的IO-x-x-rentral Ral-real rual rual rual rual rual rual rude rual rob rob rob rob roduction roduction rob roduction roduction roduction roduction roduction 一种不同的是,我们用一个Io- routt routtal- routt routtal- routt routtal- vical- roduction- routtaltra roft- vical- vict vical- vict viclegleglex rod rod- rocal- rout routd routd- le- rod- rocal- robtal-x robal-x routd routd-x rod-x rod-x rod-x rod- ro-x rod-x rod-btal-x rod-btal-xxxxxxx ro-bt-x-x le-