MAFA-net: pedestrian detection network based on multi-scale attention feature aggregation

Abstract

With pedestrian detection algorithms, balancing the trade-off between accuracy and speed remains challenging. Following the central point-based one-stage object detection paradigm, a pedestrian detection algorithm based on multi-scale attention feature aggregation (MAFA) is proposed to improve accuracy while considering real-time performance. We refer to the proposed algorithm as MAFA-Net. Through the design of deep dilate blocks, deeper features are extracted. Pedestrian attention blocks are added to mine more relevant information between features from the perspective of spatial and passage-wise dimensions, and pedestrian features are enhanced. Feature aggregation modules are used to fuse different scale features, and combine the rich high-level semantic features with the accurate location features of the low-level features. Experiments were conducted on two challenging pedestrian detection datasets, i.e., CityPersons and Caltech, using MR −2 as the evaluation index. For Caltech, MR −2 is 4.58% under reasonable conditions. For CityPersons, MR −2 is 11.47% and 10.05% under reasonable and partial occlusion conditions, which is 0.43% and 1.35% better than the suboptimal comparison detection method. The results demonstrate that a good performance is obtained, and the effectiveness and feasibility of the algorithm are verified.

Multi-Scale Deformable Transformer Encoder Based Single-Stage Pedestrian Detection

“…Each pixel in these three maps represents a confidence score, the corresponding logarithm height, and the offsets of the center position in x and y directions respectively. Most single-stage methods focus on the design of multi-level features [13][14][15][16][17]. For example, [14,17] established a feature pyramid network (FPN) similar architecture but modulates multi-scale feature maps with channel and spatial attention weights before up-sampling.…”

“…Most single-stage methods focus on the design of multi-level features [13][14][15][16][17]. For example, [14,17] established a feature pyramid network (FPN) similar architecture but modulates multi-scale feature maps with channel and spatial attention weights before up-sampling.…”