Bounding Box Alignment Based Pedestrian Crossing Collision Avoidance Using Convolution Neural Networks


Arun Kumar
Sunil Kumar S Manvi


Pedestrian detection is a challenging task for autonomous vehicles in an urban environment. Pedestrian in videos has a Variety of appearances such as occlusion and body poses and there is a proposal shift problem in pedestrian detection that cause the loss of parts such as legs and head. To address such a problem, we suggest partlevel convolution neural networks based method for pedestrian recognition using saliency map and boundary box framework in this paper. The proposed method consists of two sub-networks: person-detection and alignment. We use saliency map along with weights in the detection sub-network to remove false detections such as lamp posts and trees. The alignment network employs confidence map for better prediction of pedestrian alignment. The method is implemented and analyzed on various data sets and it hass been observed that the proposed method has better accuracy and low false positives than the existing methods.


How to Cite
Arun Kumar, & Sunil Kumar S Manvi. (2020). Bounding Box Alignment Based Pedestrian Crossing Collision Avoidance Using Convolution Neural Networks. International Journal of Next-Generation Computing, 11(2), 125–136.


  1. Felzenszwalb,P., McAllester,D., Ramanan,D., et al: “A discriminatively trained, multiscale, deformable part model,†in Proc.Int.conf. IEEE Conference on Computer Vision and Pattern Recognition., 2008, pp. 1063-6919.
  2. Felzenszwalb,P.F., Girshick,R.B., McAllester,D., et al.: “Object detection with discriminatively trained part-based models,â€IEEE Transactions on Pattern Analysis and Machine Intelligence., 2010, 32, ( 9), pp. 1627–1645.
  3. Wang, X., Jung, C., Hero, A. O., et al.: ‘Part-level fully convolutional networks for pedestrian detection’, in Proc.Int.conf. IEEE on Acoustics, Speech, and Signal Processing (ICASSP). IEEE., 2017, pp. 2267–2271.
  4. Yonglong,T., Ping,L., “Deep Learning Strong Parts for Pedestrian Detection,†in Proc. IEEE Int.Conf. Intell. Transp. Syst., 2016, pp. 1904-1912.
  5. Jie.L., Xingkun,G., Nianyuan.B., “Deep convolutional neural networks for pedestrian detection with skip pooling,†in Proc. IEEE Int.Conf. International Joint Conference on Neural Networks (IJCNN)., 2017,pp.2161-4407.
  6. Chen,Qi., Wenhui,J., Yanyun,Z., “Part-based deep network for pedestrian detection in surveillance videos,â€in Proc. IEEE Int. Conf. Visual Communications and Image Processing (VCIP), 2015, pp. 649–654.