{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T16:42:15Z","timestamp":1761324135734,"version":"build-2065373602"},"reference-count":29,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2018,1,18]],"date-time":"2018-01-18T00:00:00Z","timestamp":1516233600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Recently, deep learning techniques have had a practical role in vehicle detection. While much effort has been spent on applying deep learning to vehicle detection, the effective use of training data has not been thoroughly studied, although it has great potential for improving training results, especially in cases where the training data are sparse. In this paper, we proposed using hard example mining (HEM) in the training process of a convolutional neural network (CNN) for vehicle detection in aerial images. We applied HEM to stochastic gradient descent (SGD) to choose the most informative training data by calculating the loss values in each batch and employing the examples with the largest losses. We picked 100 out of both 500 and 1000 examples for training in one iteration, and we tested different ratios of positive to negative examples in the training data to evaluate how the balance of positive and negative examples would affect the performance. In any case, our method always outperformed the plain SGD. The experimental results for images from New York showed improved performance over a CNN trained in plain SGD where the F1 score of our method was 0.02 higher.<\/jats:p>","DOI":"10.3390\/rs10010124","type":"journal-article","created":{"date-parts":[[2018,1,18]],"date-time":"2018-01-18T12:19:48Z","timestamp":1516277988000},"page":"124","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["A CNN-Based Method of Vehicle Detection from Aerial Images Using Hard Example Mining"],"prefix":"10.3390","volume":"10","author":[{"given":"Yohei","family":"Koga","sequence":"first","affiliation":[{"name":"Center for Spatial Information Science (CSIS), University of Tokyo, 5-1-5 Kashiwanoha, Kashiwa-shi, Chiba 2778568, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7262-4566","authenticated-orcid":false,"given":"Hiroyuki","family":"Miyazaki","sequence":"additional","affiliation":[{"name":"Center for Spatial Information Science (CSIS), University of Tokyo, 5-1-5 Kashiwanoha, Kashiwa-shi, Chiba 2778568, Japan"}]},{"given":"Ryosuke","family":"Shibasaki","sequence":"additional","affiliation":[{"name":"Center for Spatial Information Science (CSIS), University of Tokyo, 5-1-5 Kashiwanoha, Kashiwa-shi, Chiba 2778568, Japan"}]}],"member":"1968","published-online":{"date-parts":[[2018,1,18]]},"reference":[{"key":"ref_1","unstructured":"(2017, November 30). Digital Globe. Available online: https:\/\/www.digitalglobe.com\/."},{"key":"ref_2","unstructured":"(2017, November 30). Planet Labs. Available online: https:\/\/www.planet.com\/."},{"key":"ref_3","unstructured":"(2017, November 30). Black Sky. Available online: https:\/\/www.blacksky.com\/."},{"key":"ref_4","unstructured":"(2017, November 30). NTT Geospace. Available online: http:\/\/www.ntt-geospace.co.jp\/."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23\u201328). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR\u201914), Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","article-title":"Selective Search for Object Recognition","volume":"104","author":"Uijlings","year":"2013","journal-title":"Int. J. Comput. Vis."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast R-CNN. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV\u201915), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_9","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 7\u201312). Faster R-CNN: Towards real-time object detection with region proposal networks. Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS\u201915), Montreal, QC, Canada."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_11","first-page":"21","article-title":"SSD: Single Shot MultiBox Detector","volume":"Volume 9905","author":"Liu","year":"2016","journal-title":"Lecture Notes in Computer Science, Proceedings of the ECCV 2016: Computer Vision\u2014ECCV 2016, Amsterdam, The Netherlands, 8\u201316 October 2016"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1109\/LGRS.2014.2309695","article-title":"Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks","volume":"11","author":"Chen","year":"2014","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_13","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201325). Histograms of oriented gradients for human detection. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), San Diego, CA, USA."},{"key":"ref_14","first-page":"158","article-title":"Vehicle Detection in Satellite Images by Incorporating Objectness and Convolutional Neural Network","volume":"4","author":"Qu","year":"2016","journal-title":"J. Ind. Intell. Inf."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Cheng, M.M., Zhang, Z., Lin, W.Y., and Torr, P. (2014, January 23\u201328). BING: Binarized Normed Gradients for Objectness Estimation at 300fps. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.414"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tang, T., Zhou, S., Deng, Z., Zou, H., and Lei, L. (2017). Vehicle Detection in Aerial Images Based on Region Convolutional Neural Networks and Hard Negative Example Mining. Sensors, 17.","DOI":"10.3390\/s17020336"},{"key":"ref_17","unstructured":"(2017, July 27). Car Localization and Counting with Overhead Imagery, an Interactive Exploration. Available online: https:\/\/medium.com\/the-downlinq\/car-localization-and-counting-with-overhead-imagery-an-interactive-exploration-9d5a029a596b."},{"key":"ref_18","first-page":"785","article-title":"A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning","volume":"Volume 9907","author":"Mundhenk","year":"2016","journal-title":"Lecture Notes in Computer Science, Proceedings of the ECCV 2016: Computer Vision\u2014ECCV 2016, Amsterdam, The Netherlands, 8\u201316 October 2016"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1023\/A:1007614523901","article-title":"Improved Boosting Algorithms Using Confidence-rated Predictions","volume":"37","author":"Schapire","year":"1999","journal-title":"Mach. Learn."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., and Girshick, R. (2016, January 27\u201330). Training Region-Based Object Detectors with Online Hard Example Mining. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref_23","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on International Conference on Machine Learning (ICML\u201915), Lille, France."},{"key":"ref_24","unstructured":"(2017, July 27). CS231n: Convolutional Neural Networks for Visual Recognition. Available online: http:\/\/cs231n.github.io\/optimization-1\/#gd."},{"key":"ref_25","unstructured":"(2017, July 27). UFLDL Tutorial. Available online: http:\/\/ufldl.stanford.edu\/tutorial\/supervised\/OptimizationStochasticGradientDescent\/."},{"key":"ref_26","unstructured":"(2017, July 27). Neural Networks and Deep Learning (CHAPTER 2). Available online: http:\/\/neuralnetworksanddeeplearning.com\/chap2.html."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","article-title":"Object Detection with Discriminatively Trained Part-Based Models","volume":"32","author":"Felzenszwalb","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_28","unstructured":"Kingma, D.P., and Ba, J. (arXiv, 2014). Adam: A Method for Stochastic Optimization, arXiv."},{"key":"ref_29","unstructured":"Liu, K., and Mattyus, G. (2017, November 30). DLR 3k Munich Vehicle Aerial Image Dataset. Available online: http:\/\/pba-freesoftware.eoc.dlr.de\/3K_VehicleDetection_dataset.zip."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/1\/124\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:51:43Z","timestamp":1760194303000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/1\/124"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1,18]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2018,1]]}},"alternative-id":["rs10010124"],"URL":"https:\/\/doi.org\/10.3390\/rs10010124","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2018,1,18]]}}}