Evaluation and Empirical Study of Image Enhancement Strategies for Small Object Detection in Remote Sensing

Runxing Song

doi:10.54097/h4f28d98

Authors

Runxing Song School of Mechanical Engineering, Nanjing University of Science & Technology, Nanjing, Jiangsu, 210094, China

DOI:

https://doi.org/10.54097/h4f28d98

Keywords:

Optical remote sensing, small object detection, image enhancement, degradation perception

Abstract

Optical remote sensing small object detection is limited by the low proportion of target pixels, complex backgrounds, and image degradation. To avoid equating visual enhancement with detection benefits, this paper analyzes degradation perception in image enhancement, combining image degradation, enhancement processing, target area visibility, and detection feedback, and empirically conducts the analysis based on the Northwestern Polytechnical University Very-High-Resolution 10-class (NWPU VHR-10) dataset. This paper combines the Common Objects in Context (COCO) small target area threshold and the relative area of the remote sensing target frame, and proposes a screening rule that the target frame area does not exceed 1% of the image area. Then, 30 positive samples were simulated for downsampling, blurring, noise, and haze degradation, comparing bicubic interpolation, Contrast Limited Adaptive Histogram Equalization (CLAHE), sharpening, dehazing, and fusion enhancement. After further training the You Only Look Once version 8 nano (YOLOv8n) detector, the mAP50 values for the original, degraded, and enhanced images were 0.921, 0.851, and 0.826, respectively, and the recall values were 0.871, 0.789, and 0.753, respectively. The results show that edge texture enhancement cannot be directly equated with detection benefits; enhancement evaluation should focus on full-image fidelity, target area indicators, and authentic detection feedback.

Downloads

Download data is not yet available.

References

[1] Gui S, Song S, Qin R, Tang Y. Remote sensing object detection in the deep learning era-a review. Remote Sensing, 2024, 16(2): 327. DOI: https://doi.org/10.3390/rs16020327

[2] Hua W, Chen Q. A survey of small object detection based on deep learning in aerial images. Artificial Intelligence Review, 2025, 58(6): 162. DOI: https://doi.org/10.1007/s10462-025-11150-9

[3] Liu J, Pan B, Shi Z. CR-Famba: A frequency-domain assisted Mamba for thin cloud removal in optical remote sensing imagery. IEEE Transactions on Multimedia, 2025, 27: 5659-5668. DOI: https://doi.org/10.1109/TMM.2025.3542976

[4] Ning J, Xie L, Yin J, Liu Y. Cloud removal advances: a comprehensive review and analysis for optical remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, 18: 15914-15930. DOI: https://doi.org/10.1109/JSTARS.2025.3580718

[5] Li N, Cheng L, Ji C, Chen H, Geng W, Yang W. Airport detection in remote sensing real-open world using deep learning. Engineering Applications of Artificial Intelligence, 2023, 122: 106083. DOI: https://doi.org/10.1016/j.engappai.2023.106083

[6] Wang Y, Bashir S M A, Khan M, Ullah Q, Wang R, Song Y, Guo Z, Niu Y. Remote sensing image super-resolution and object detection: benchmark and state of the art. Expert Systems with Applications, 2022, 197: 116793. DOI: https://doi.org/10.1016/j.eswa.2022.116793

[7] He K, Sun J, Tang X. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353. DOI: https://doi.org/10.1109/TPAMI.2010.168

[8] Wang Y, Cheng J. A novel cloud removal method by fusing features from SAR and neighboring optical remote sensing images. PLOS ONE, 2025, 20(9): e0332898. DOI: https://doi.org/10.1371/journal.pone.0332898

[9] Tian L, Cao Y, He B, Zhang Y, He C, Li D. Image enhancement driven by object characteristics and dense feature reuse network for ship target detection in remote sensing imagery. Remote Sensing, 2021, 13(7): 1327. DOI: https://doi.org/10.3390/rs13071327

[10] Meng L, Li H, Han H, Xu M, Wu J, Hou S, Duan W. Progressive enhancement of foreground features for salient object detection in optical remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, 18: 7572-7591. DOI: https://doi.org/10.1109/JSTARS.2025.3545681

[11] Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Dollar P, Zitnick C L. Microsoft COCO: common objects in context. Computer Vision-ECCV 2014, Lecture Notes in Computer Science, 2014, 8693: 740-755. DOI: https://doi.org/10.1007/978-3-319-10602-1_48

[12] Jocher G, Qiu J, Chaurasia A. Ultralytics YOLO. GitHub repository, 2023. Available: https://github.com/ultralytics/ultralytics.

[13] Cheng G, Han J, Zhou P, Guo L. Multi-class geospatial object detection and geographic image classification based on collection of part detectors. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 98: 119-132. DOI: https://doi.org/10.1016/j.isprsjprs.2014.10.002

[14] Li K, Wan G, Cheng G, Meng L, Han J. Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 159: 296-307. DOI: https://doi.org/10.1016/j.isprsjprs.2019.11.023

[15] Xia G-S, Bai X, Ding J, Zhu Z, Belongie S, Luo J, Datcu M, Pelillo M, Zhang L. DOTA: A large-scale dataset for object detection in aerial images. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 3974-3983. DOI: https://doi.org/10.1109/CVPR.2018.00418

[16] Zhao Y, Lv W, Xu S, Wei J, Wang G, Dang Q, Liu Y, Chen J. DETRs beat YOLOs on real-time object detection. arXiv:2304.08069v3, 2024. DOI: https://doi.org/10.1109/CVPR52733.2024.01605