Traffic participant detection, which locates targets participating in road traffic such as vehicles and humans, is a critical research goal in autonomous driving and intelligent transportation technology, in which targets of various scales are challenging to handle. To address this problem, we propose an accurate and efficient traffic participant detector called FM-RepPoints to increase detection precision of multi-scale targets via optimized features and localization confidence. We first present a parameter-efficient backbone Dilated-ResNeSt to extract complicated urban scene features with less inference time. An adaptive attention module is then added to calibrate the features according to the corresponding targets. Moreover, we set the multi-scale localization confidence for traffic participants of various scales based on the sensitivity analysis. The proposed network outperforms the basic network by 3.3 points mAP; the accuracy of vehicles and humans is improved by 4.5% and 2.1%, respectively. Compared with state-of-the-art algorithms, the proposed method achieves the highest accuracy while maintaining average inference speed, thereby accomplishing the best speed-accuracy trade-off.
LinCShiYZhangJ, et al. An anchor-free detector and R-CNN integrated neural network architecture for environmental perception of urban roads. Proc IMechE, Part D: J Automobile Engineering2021; 235: 2964–2973.
2.
CordtsMOmranMRamosS, et al. The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp.3213–3223. IEEE.
3.
WuXSahooDHoiSCH. Recent advances in deep learning for object detection. Neurocomputing2020; 396: 39–64.
4.
GirshickRDonahueJDarrellT, et al. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp.580–587. IEEE.
5.
GirshickR. Fast R-CNN. In: Proceedings of the IEEE international conference on computer vision, 2015, pp.1440–1448. IEEE.
6.
RenSHeKGirshickR, et al. Faster R-CNN: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst2015; 28: 91–99.
7.
HeKGkioxariGDollárP, et al. Mask R-CNN
. In: Proceedings of the IEEE international conference on computer vision, 2017, pp.2961–2969. IEEE.
8.
CaiZVasconcelosN. Cascade R-CNN: Delving into high-quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp.6154–6162. IEEE.
9.
RedmonJYolovFA. An incremental improvement. arXiv preprint arXiv:1804.02767, 2018.
10.
BochkovskiyAWangCYYolovLHYM. Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934, 2020.
11.
GeZLiuSWangF, et al. Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430, 2021.
12.
LiuWAnguelovDErhanD, et al. SSD: single shot multibox detector. In: European conference on computer vision, 2016, pp.21–37. Cham: Springer, 2016.
13.
ZhangSWenLBianX, et al. Single-shot refinement neural network for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp.4203–4212. IEEE.
14.
ZhaoQShengTWangY, et al. M2Det: a single-shot object detector based on multi-level feature pyramid network. In: AAAI. Proceedings of the AAAI conference on artificial intelligence, 2019, vol. 33, pp.9259–9266. AAAI.
15.
YangZLiuSHuH, et al. Reppoints: point set representation for object detection. In: Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp.9657–9666. IEEE.
16.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp.770–778. IEEE.
17.
ZhangHWuCZhangZ, et al. Resnest: Split-attention networks. arXiv preprint arXiv:2004.08955, 2020.
18.
XieSGirshickRDollárP, et al. Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp.1492–500. IEEE.
19.
GaoSHChengMMZhaoK, et al. Res2net: a new multi-scale backbone architecture. IEEE Trans Pattern Anal Mach Intell2021; 43(2): 652–662.
20.
LiXWangWHuX, et al. Selective kernel networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp.510–519. IEEE.
21.
LinTYDollárPGirshickR, et al. Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp.2117–2125. IEEE.
22.
DaiJQiHXiongY, et al. Deformable convolutional networks. In: Proceedings of the IEEE international conference on computer vision, 2017, pp.764–773. IEEE.
23.
ZhuXHuHLinS, et al. Deformable ConvNets v2: more deformable, better results. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp.9308–9316. IEEE.
24.
NeubeckAVan GoolL. Efficient non-maximum suppression. In: 18th international conference on pattern recognition (ICPR’06), 2006, pp.850–855. IEEE.
25.
JiangBLuoRMaoJ, et al. Acquisition of localization confidence for accurate object detection. In: Proceedings of the European conference on computer vision (ECCV), 2018, pp.784–799. Cham: Springer.
26.
TianZShenCChenH, et al. Fcos: Fully convolutional one-stage object detection. In: Proceedings of the IEEE/CVF international conference on computer vision, 2019, pp.9627–9636. IEEE.
27.
ZhangSChiCYaoY, et al. Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp.9759–9768. IEEE.
28.
LinTYGoyalPGirshickR, et al. Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, 2017, pp.2980–2988. IEEE.
29.
WangQWuBZhuP, et al. ECA-net: efficient channel attention for deep convolutional neural networks. In: IEEE Publications/CVF conference on computer vision and pattern recognition (CVPR), 2020. IEEE.
HuJShenLSunG. Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp.7132–7141. IEEE.
32.
WooSParkJLeeJY, et al. Cbam: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), 2018, pp.3–19. Cham: Springer.
33.
ChenKWangJPangJ, et al. MMDetection: open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155, 2019.
34.
LinTYMaireMBelongieS, et al. Microsoft coco: common objects in context. In: European conference on computer vision, 2014, pp.740–755. Cham: Springer
35.
YuFKoltunVFunkhouserT. Dilated residual networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp.472–480. IEEE.
36.
CaoYXuJLinS, et al. Gcnet: non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE/CVF international conference on computer vision workshops, 2019.
37.
LiuHLiuFFanX, et al. Polarized self-attention: towards high-quality pixel-wise regression. arXiv preprint arXiv:2107.00782, 2021.
38.
CaoYChenKLoyCC, et al. Prime sample attention in object detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp.11583–11591. IEEE.
