Pedestrian Detection by Novel Axis-Line Representation and Regression Pattern

Abstract

The pattern of bounding box representation and regression has long been dominant in CNN-based pedestrian detectors. Despite the method’s success, it cannot accurately represent location, and introduces unnecessary background information, while pedestrian features are mainly located in axis-line areas. Other object representations, such as corner-pairs, are not easy to obtain by regression because the corners are far from the axis-line and are greatly affected by background features. In this paper, we propose a novel detection pattern, named Axis-line Representation and Regression (ALR), for pedestrian detection in road scenes. Specifically, we design a 3-d axis-line representation for pedestrians and use it as the regression target during network training. A line-box transformation method is also proposed to fit the widely used box-annotations. Meanwhile, we explore the influence of deformable convolution base-offset on detection performance and propose a base-offset initialization strategy to further promote the gain brought by ALR. Notably, the proposed ALR pattern can be introduced into both anchor-based and anchor-free frameworks. We validate the effectiveness of ALR on the Caltech-USA and CityPersons datasets. Experimental results show that our approach outperforms the baseline significantly through simple modifications and achieves competitive accuracy with other methods without bells and whistles.

Two-Stage Pedestrian Detection Model Using a New Classification Head for Domain Generalization

“…In the last decade, deep learning has enabled significant progress in a variety of applications including object detection [1,2], face recognition [3], iris recognition [4], genetic algorithms applied to CNNs [5,6], rock lithological classification [7], trademark image retrieval [8], and semantic segmentation [9], among others. Pedestrian detection is one of the key tasks in computer vision, for which several models have been developed in the past few years [10][11][12][13][14][15][16][17][18][19]. The performance has shown a steady improvement over time, especially with the boom of deep-learning-based methods, with certain benchmarks approaching human performance [20], e.g., the Caltech benchmark [21].…”