Abstract
The intelligent processing and utilization of visual perception information is the key technology of Internet of Things (IoT), and object detection based on deep learning is of great significance for improving the intelligence and security of IoT. Due to the influence of factors such as changes in the state of object in actual scene, occlusion and background changes, object detection method of deep learning still has following problems: features extracted by backbone network are noisy and not representative, the positive and negative samples are not balanced, and labeled object is inaccurate due to occlusion. Therefore, this paper proposes an object detection method based on global feature augmentation and adaptive regression. HRFPN extracts more representative high-resolution features and performs global augmentation, which can effectively distinguish feature differences between object and background. In training phase, uniform sampling is introduced to mine hard samples, and the positive and negative samples in RPN phase are balanced to improve detection performance, and adaptive bounding box regression loss is proposed to reduce the influence of object occlusion and boundary blur. Experimental results on PASCAL VOC2007 and MS COCO2017 datasets show that the proposed detection method is superior to the latest methods such as Cascade RCNN, CornerNet and Mask RCNN, which has better robustness and accuracy.
Similar content being viewed by others
Reference
Cai Z, Fan Q, R S Feris et al (2016) A unifified multi-scale deep convolutional neural network for fast object detection. In: European conference on computer vision, pp 354–370
Hu ZB, Xu XL, Su QH et al (2019) Grey prediction evolution algorithm for global optimization. Appl Math Model 79:145–160
Xu L, Wang J, Wang H et al (2020) BP neural network-based ABEP performance prediction for mobile Internet of Things communication systems. Neural Comput Appl 32(20):16025–16041
Cai W, Li J, Xie Z, Zhao T et al (2018) Street object detection based on faster R-CNN. In: Chinese control conference (CCC), pp 9500–9503
Dalal R, Moh T (2018) Fine-grained object detection using transfer learning and data augmentation. In: Advances in social networks analysis and mining (ASONAM), pp 893–896
Dai J, Qi H, Xiong Y et al (2017) Deformable convolutional networks. In: International conference on computer vision, pp 764–773
Xu L, Wang H, Gulliver TA (2020) Outage probability performance analysis and prediction for mobile IoV networks based on ICS-BP neural network. IEEE Internet Things J
Mane S, Mangale S (2018) Moving object detection and tracking using convolutional neural networks. In: International conference on intelligent computing and control systems (ICICCS), pp 1809–1813
Wu X, Hong D, Ghamisi P et al (2019) LW-ODF: a light-weight object detection framework for optical remote sensing imagery. In: International geoscience and remote sensing symposium (IGARSS), pp 1462–1465
Kumaran N, Reddy US (2017) Object detection and tracking in crowd environment—a review. In: International conference on inventive computing and informatics (ICICI), pp 777–782
Xu X, Hu ZB, Su Q et al (2020) Multivariable grey prediction evolution algorithm: a new metaheuristic. Appl Soft Comput 89:106086
Zhang X, Zhu L (2019) Fast salient object detection based on multi-scale feature aggression. In: Chinese control and decision conference (CCDC), pp 5734–5738
Zhao Z, Zheng P, Xu S et al (2019) Object detection with deep learning: a review. Trans Neural Netw Learn Syst 30:3212–3232
Yang X, Fu K, Sun H et al (2018) Object detection with head direction in remote sensing images based on rotational region CNN. In: International geoscience and remote sensing symposium, pp 2507–2510
Zhang Q, Wan C, S Bian (2018) Research on vehicle object detection method based on convolutional neural network. In: International symposium on computational intelligence and design (ISCID), pp 271–274
Ross G, Jeff D, Trevor D et al (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Conference on computer vision and pattern recognition (CVPR), pp 580–587
Ouadiay F Z, Bouftaih H, Bouyakhf EH et al (2018) Simultaneous object detection and localization using convolutional neural networks. In: Intelligent systems and computer vision (ISCV), pp 1–8
He K, Zhang X, Ren S et al (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904–1916
Ross G (2015) Fast-CNN. In: IEEE international conference on computer vision (ICCV), pp 1440–1448
Ren S, He K, Ross G et al (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Neural information processing systems, pp 91–99
Cai Z, Vasconcelos N (2018) Cascade R-CNN: delving into high quality object detection. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 6154–6162
He K, Georgia G, Piot D et al (2020) Mask RCNN. IEEE Trans Pattern Anal Mach Intell 42(2):386–397. https://doi.org/10.1109/TPAMI.2018.2844175
Joseph R, Santosh D, Ross G et al (2016) You only look once: unified, real-time object detection. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 779–788
Redmom J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 6517–6525
Xiao D, Shan F, Li Z et al (2019) An object detection model based on improved Tiny-Yolov3 under the environment of mining truck. IEEE Access 7:123757–123764
Bochkovskiy A, Wang C Y, Liao H. YOLOv4: optimal speed and accuracy of object detection [EB/OL]. (2020-04-23) [2020-10-20]. http://ariv.xilesou.top/pdf/2004.10934
Liu W, Anguelov D, Erhan D et al (2016) SSD: single shot multibox detector. In: European conference on computer vision. Springer, Cham, pp 21–37
Fu C Y, Liu W, Ranga A et al. DSSD: deconvolutional single shot detector [EB/OL] (2017-01-23) [2020-10-20]. http://ariv.xilesou.top/pdf/1701.06659.pdf
Jeong J et al. Enhancement of SSD by concatenating feature maps for object detection [EB/OL] (2017-05-26) [2020-10-20]. http://ariv.xilesou.top/pdf/1705.09587.pdf
Li Z, Zhou F. FSSD: feature fusion single shot multibox detector [EB/OL] (2018-05-17) [2020-10-20]. http://ariv.xilesou.top/pdf/1712.00960.pdf
Lin TY, Goyal P, Girshick R et al (2017) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell PP(99):2999–3007
Law H, Deng J (2018) CornerNet: detecting objects as paired keypoints. In: European conference on computer vision, pp 642–656
Zhou X, Wang D, Philipp K, et al. Objects as points [EB/OL]. (2019-04-25) [2020-10-20]. http://ariv.xilesou.top/pdf/1904.07850.pdf
Sun K, Xiao B, Liu D et al (2019) Deep high-resolution representation learning for human pose estimation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1–12
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778
Tsung-Yi L, Piotr D, Ross G et al (2017) Feature pyramid networks for object detection. In: IEEE conference on computer vision and pattern recognition, pp 936–944
Acknowledgements
This research was funded by National Natural Science Foundation of China (Grant No. 61702295), the Shandong Province Natural Science Foundation (Grant No. ZR2020QF003), the Opening Foundation of Key Laboratory of Opto-Technology and Intelligent Control (Lanzhou Jiaotong University), the Ministry of Education (Grant No. KFKT2020-09), the Shandong Province Postdoctoral Innovation Project (Grant No. 201703032), the Shandong Province Colleges and Universities Young Talents Initiation Program (Grant No. 2019KJN047), and the Doctoral Fund of QUST (Grant Nos. 1203043003480, 010029029).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, H., Dong, Y., Xu, L. et al. Object detection method based on global feature augmentation and adaptive regression in IoT. Neural Comput & Applic 33, 4119–4131 (2021). https://doi.org/10.1007/s00521-020-05633-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05633-9