Abstract
Object detection is considered as a challenging field in computer vision. Once an object has been detected, the next challenge is object localization where a rectangular boundary box is drawn around the location of detected object. The proposed framework addresses the problem of object localization by improving its precision. You only look once or YOLOv3 is one of the well-known object detection algorithm with its state-of-the-art object detection and real time capabilities. Because of this reason, the proposed scheme uses YOLOv3 as the base algorithm. In this work, COCO dataset is used to detect an object, and to improve the precision of boundary box this work make use of edge detection, thresholding and morphological operation. Also, redundant edge removal algorithm is proposed to remove redundant edges and boundary box construction algorithm draws rectangular boundary box around detected object. When compared with YOLOv3, the proposed model produces significantly better results when boundary boxes around detected object is concern.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Druzhkov, P.N., Kustikova, V.D.: A survey of deep learning methods and software tools for image classification and object detection. Pattern Recogn. Image Anal. 26, 9–15 (2016). https://doi.org/10.1134/S1054661816010065
Wojek, C., Dollar, P., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34, 743–761 (2012)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004). https://doi.org/10.1023/B:VISI.0000029664.99615.94
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
Lienhart, R., Maydt, J.: An extended set of Haar-like features for rapid object detection. In: International Conference on Image Processing (2002)
Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR (2014)
Girshick, R.: Fast R-CNN. In: International Conference on Computer Vision (2015)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)
Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. In: NIPS (2016)
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)
He, K., et al.: Mask R-CNN. In: ICCV (2017)
Erhan, D., et al.: Scalable object detection using deep neural networks. In: CVPR (2014)
Najibi, M., et al.: G-CNN: an iterative grid based object detector. In: CVPR (2016)
Yoo, D., Park, S., et al.: AttentionNet: aggregating weak directions for accurate object detection. In: CVPR (2015)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified real-time object detection. In: CVPR (2016)
Redmon, J., Farhadi, A.: YOLO9000: better faster stronger. In: CVPR (2016)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Fu, C.-Y., et al.: DSSD: Deconvolutional single shot detector. https://arxiv.org/abs/1701.06659 (2017)
Shen, Z., Liu, Z., Li, J., Jiang, Y.-G., Chen, Y., Xue, X.: DSOD: learning deeply supervised object detectors from scratch. In: ICCV (2017)
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. https://arxiv.org/abs/1804.02767 (2018)
Uijlings, J.R.R., van de Sande, K.E.A., Gevers, T., Smeulders, A.W.M.: Selective search for object recognition. Int. J. Comput. Vis. 104, 154–171 (2013). https://doi.org/10.1007/s11263-013-0620-5
Cortes, C., Vapnik, V.: Support vector network. Mach. Learn. 20, 273–297 (1995). https://doi.org/10.1007/BF00994018
Blue, S.T., Brindha, M.: Edge detection based boundary box construction algorithm for improving the precision of object detection in YOLOv. In: 10th ICCCNT (2019)
Zhang, D., Zhang, P., Wang, L.: Cell counting algorithm based on YOLOv3 and image density estimation. In: 4th International Conference on Signal and Image Processing, (2019)
Zhang, X., Zhu, X.: Vehicle Detection in the aerial infrared images via an improved YOLOv3 network. In: 4th International Conference on Signal and Image Processing (2019)
Shi, T., Liu, M, Yang, Y., Wang, P., Huang, Y.: Fast classification and detection of marine targets in complex scenes with YOLOv3. In: OCEANS 2019, Marseille (2019)
Cui, H., Yang, Y., Liu, M., Shi, T., Qi, Q.: Ship detection: an improved YOLOv3 method. In: OCEANS 2019, Marseille (2019)
Qu, H., Yuan, T., Sheng, Z., Zhang, Y.: A pedestrian detection method based on YOLOv3 Model and Image enhanced by Retinex. In: 11th CISP-BMEI (2018)
Miao, F., Tian, Y., Jin, L.: Vehicle direction detection based on yolov3. In: 11th IHMSC (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Blue, S.T., Brindha, M. (2020). An Edge Detection and Sliding Window Based Approach to Improve Object Localization in YOLOv3. In: Bhattacharjee, A., Borgohain, S., Soni, B., Verma, G., Gao, XZ. (eds) Machine Learning, Image Processing, Network Security and Data Sciences. MIND 2020. Communications in Computer and Information Science, vol 1240. Springer, Singapore. https://doi.org/10.1007/978-981-15-6315-7_13
Download citation
DOI: https://doi.org/10.1007/978-981-15-6315-7_13
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-6314-0
Online ISBN: 978-981-15-6315-7
eBook Packages: Computer ScienceComputer Science (R0)