Abstract
Owing to the innovative challenge stood by an intergovernmental military alliance, we have proposed a model to find novel solutions in the areas of data filtering/combining, visualization, and predictive analytics. Detecting tiny objects over huge zones has stayed as a major confront in satellite imagery examination. Among the confronts, the absolute quantity of pixels and topographical degree per picture are principle things. To deal with these issues, Multi-Scale Swift Detection System using COWC dataset to localize vehicles, i.e., cars in aerial imagery rapidly is implemented. We propose a model, Multiscale swift detection system that evaluates the satellite-images of an arbitrarily large size at a rate of 0.2 km2/s in the confined resolution. Forging over the TensorFlow object-detection API paper [11], this model provides an integrated tactic to various object-detection frameworks that can sprint interpretation on images of random size. The Multiscale swift detection system includes a customized version-type of YOLO, known as YOLT. The approach can hastily detect objects of infinitely various scales with comparatively less training data upon multiple sensors. It can quickly detect objects of immensely diverse scales with comparatively modest training data over several sensors. For the object detection area of the work, we use the COWC dataset, which features aerial imagery taken in different locations. Here the mean size of cars is assumed to be roughly constant. We assess bulky test-images at confined resolution and discover mAP scores of 0.2 to 0.8 for the vehicle-localization. Also computed a yield score of F1 > 0.8 attaining both the highest mAP value and rapid inference speed with the YOLT architecture.
Similar content being viewed by others
References
Ardö H, Guzhva O, Nilsson M, Herlin AH (2018) Convolutional neural network-based cow interaction watchdog. IET Comput Vis 12(2):171–177
Cars Overhead With Context dataset, Computation Engineering Division at Lawrence Livermore National Laborator, https://gdo152.llnl.gov/cowc/
Chen CP, Liu Z (2017) Broad learning system: an effective and efficient incremental learning system without the need for deep architecture. IEEE Transactions on Neural Networks and Learning Systems 29(1):10–24
Chen Z, Wang C, Wen C, Teng X, Chen Y, Guan H, Luo H, Cao L, Li J (2015) Vehicle detection in high-resolution aerial images via sparse representation and superpixels. IEEE Trans Geosci Remote Sens 54(1):103–116
Chen J, Zheng H, Lin X, Wu Y, Su M (2018) A novel image segmentation method based on fast density clustering algorithm. Eng Appl Artif Intell 73:92–110
Cheng G, Han J (2016) A survey on object detection in optical remote sensing images. ISPRS J Photogramm Remote Sens 117:11–28
Ding P, Zhang Y, Deng WJ, Jia P, Kuijper A (2018) A light and faster regional convolutional neural network for object detection in optical remote sensing images. ISPRS J Photogramm Remote Sens 141:208–218
Glagolevs J, Freivalds K (2017, November) Logo detection in images using HOG and SIFT. In: 2017 5th IEEE workshop on advances in information, electronic and electrical engineering (AIEEE). IEEE, pp 1–5
Gonzalez LF, Montes GA, Puig E, Johnson S, Mengersen K, Gaston KJ (2016) Unmanned aerial vehicles (UAVs) and artificial intelligence revolutionizing wildlife monitoring and conservation. Sensors 16(1):97
Huang J, Rathod V, Sun C, Zhu M, Korattikara A, Fathi A, … Murphy K (2017) Speed/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7310–7311
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016, October) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, Cham, pp 21–37
Liu Q, Xiang X, Wang Y, Luo Z, Fang F (2020) Aircraft detection in remote sensing image based on corner clustering and deep learning. Eng Appl Artif Intell 87:103333
Rastegari M, Ordonez V, Redmon J, Farhadi A (2016, October) Xnor-net: Imagenet classification using binary convolutional neural networks. In: European conference on computer vision. Springer, Cham, pp 525–542
Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779–788
Ren S, He K, Girshick R, Sun J (2016) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Shao W, Kawakami R, Yoshihashi R, You S, Kawase H, Naemura T (2020) Cattle detection and counting in UAV images based on convolutional neural networks. Int J Remote Sens 41(1):31–52
Shrivastava S, Aggarwal A, Chattopadhyay P (2020) Broad neural network for change detection in aerial images. In: Emerging Technology in Modelling and Graphics. Springer, Singapore, pp 327–339
Song S, Xu B, Yang J (2016) SAR target recognition via supervised discriminative dictionary learning and sparse representation of the SAR-HOG feature. Remote Sens 8(8):683
Van Etten A (2019, January) Satellite imagery multiscale rapid detection with windowed networks. In: 2019 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 735–743
van Gemert JC, Verschoor CR, Mettes P, Epema K, Koh LP, Wich S (2014, September) Nature conservation drones for automatic localization and counting of animals. In: European conference on computer vision. Springer, Cham, pp 255–270
Wu H, Zhang H, Zhang J, Xu F (2015) Typical target detection in satellite images based on convolutional neural networks. In: 2015 IEEE international conference on systems, man, and cybernetics. IEEE, pp 2956–2961
Availability of supporting data
The data will be provided based on data request by the evaluation team.
Funding
This Research Received no specific grant from any funding agency in the public, commercial or not-for-profit sectors.
Author information
Authors and Affiliations
Contributions
The Author’s have developed a holistic framework for vehicle detection in high resolution images.
Corresponding author
Ethics declarations
Ethical approval and consent to participate
Not applicable.
Consent for publication
All the authors of this paper have shown their Participation voluntarily.
Competing interests
The authors of this research article declares that no conflict of interest in preparing this research article.
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
K, L., Karnick, S., Ghalib, M.R. et al. A novel method for vehicle detection in high-resolution aerial remote sensing images using YOLT approach. Multimed Tools Appl 81, 23551–23566 (2022). https://doi.org/10.1007/s11042-022-12613-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12613-9