Overlapping Box Suppression and Merging Algorithms for Window-Based Object Detection

• Autorzy: Kos Aleksandra

Identyfikatory

DOI

10.2478/fcds-2025-0016

• Języki publikacji: EN

Abstrakty

EN

In this manuscript, we extend the Overlapping Box Suppression (OBS) algorithm, a novel approach designed to enhance window-based object detection systems by reducing false-positive detections. While window-based methods are commonly used for small object detection, they often face challenges due to partially visible objects and intersecting detection windows. To address this, the proposed OBS algorithm uses the detection window coordinates to effectively filter out redundant partial detections, improving detection quality. Additionally, we introduce a novel Overlapping Box Merging (OBM) algorithm, which further refines detection results by combining partial detections into a single, more accurate detection. Together, OBS and OBM offer a robust solution for handling overlapping and fragmented detections. We evaluate this combined global filtering block on sequences from the SeaDronesSee dataset, demonstrating superior performance across multiple object detection metrics compared to traditional NMS-based filtering methods.

Słowa kluczowe

EN

deep learning; object detection; window-based object detection; small object detection; Overlapping Box Suppression; Overlapping Box Merging

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Foundations of Computing and Decision Sciences
• Rocznik: 2025
• Tom: Vol. 50, No. 3
• Strony: 403--23
• Opis fizyczny: Bibliogr. 32 poz., rys., tab.

Twórcy

autor

Kos Aleksandra

• Institute of Robotics and Machine Intelligence, Poznan University of Technology, Poznań, Poland

Bibliografia

• [1] Akyon F. C., Onur Altinuc S., and Temizel A. Slicing aided hyper inference and fine-tuning for small object detection. In 2022 IEEE International Conference on Image Processing (ICIP). IEEE, Oct. 2022.
• [2] Bewley A., Ge Z., Ott L., Ramos F., and Upcroft B. Simple online and realtime tracking. In 2016 IEEE international conference on image processing (ICIP), pages 3464-3468. IEEE, 2016.
• [3] Bodla N., Singh B., Chellappa R., and Davis L. S. Soft-NMS - improving object detection with one line of code. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 5562–5570, 2017.
• [4] Carion N., Massa F., Synnaeve G., Usunier N., Kirillov A., and Zagoruyko S. End-to-end object detection with transformers. In Vedaldi A., Bischof H., Brox T., and Frahm J.-M., editors, Computer Vision - ECCV 2020, pages 213-229, Cham, 2020. Springer International Publishing.
• [5] Cheng G., Yuan X., Yao X., Yan K., Zeng Q., Xie X., and Han J. Towards large-scale small object detection: Survey and benchmarks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
• [6] Duan C., Wei Z., Zhang C., Qu S., and Wang H. Coarse-grained density map guided object detection in aerial images. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2789-2798, 2021.
• [7] Gilg J., Teepe T., Herzog F., Wolters P., and Rigoll G. Do we still need non-maximum suppression? accurate confidence estimates and implicit duplication modeling with iou-aware calibration. In 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 4838-4847, 2024.
• [8] Girshick R. Fast R-CNN. In 2015 IEEE International Conference on Computer Vision (ICCV), pages 1440-1448, 2015.
• [9] Kos A., Majek K., and Belter D. Where to look for tiny objects? ROI prediction for tiny object detection in high resolution images. In 2022 17th International Conference on Control, Automation, Robotics and Vision (ICARCV), pages 721-726. IEEE, 2022.
• [10] Kos A., Majek K., and Belter D. Enhanced lightweight detection of small and tiny objects in high-resolution images using object tracking-based region of interest proposal. Engineering Applications of Artificial Intelligence, 153: 110852, 2025.
• [11] Kos A., Majek K., and Belter D. SegTrackDetect: A window-based framework for tiny object detection via semantic segmentation and tracking. SoftwareX, 30: 102110, 2025.
• [12] Kos, Aleksandra. Overlapping Box Suppression Algorithm for Window-Based Object Detection. In Progress in Polish Artificial Intelligence Research 5 : Proceedings of the 5th Polish Conference on Artificial Intelligence (PP-RAI’2024), 18-20.04.2024, Warsaw, Poland, pages 325-330. Politechnika Warszawska, 2024.
• [13] Koyun O. C., Keser R. K., Akkaya ˙I. B., and Töreyin B. U. Focus-and-detect: A small object detection framework for aerial images. Signal Processing: Image Communication, 104: 116675, 2022.
• [14] Li Y., Mao H., Girshick R., and He K. Exploring plain vision transformer backbones for object detection. In Avidan S., Brostow G., Cissé M., Farinella G. M., and Hassner T., editors, Computer Vision - ECCV 2022, pages 280-296, Cham, 2022. Springer Nature Switzerland.
• [15] Lin T.-Y., Maire M., Belongie S., Hays J., Perona P., Ramanan D., Dollár P., and Zitnick C. L. Microsoft COCO: Common objects in context. In European conference on computer vision, pages 740-755. Springer, 2014.
• [16] Ozge Unel F., Ozkalayci B. O., and Cigla C. The power of tiling for small object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 0-0, 2019.
• [17] Pan Y. and Dong F. Suppression and enhancement of overlapping bounding boxes scores in object detection. In 2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), pages 1-4, 2019.
• [18] Pirinen A. and Sminchisescu C. Deep reinforcement learning of region proposal networks for object detection. pages 6945-6954, 2018.
• [19] Rosenfeld A. and Thurston M. Edge and curve detection for visual scene analysis. IEEE Transactions on computers, 100(5): 562-569, 1971.
• [20] Salscheider N. O. Featurenms: Non-maximum suppression by learning feature embeddings. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 7848-7854, 2021.
• [21] Shapira A., Zolfi A., Demetrio L., Biggio B., and Shabtai A. Phantom sponges: Exploiting non-maximum suppression to attack deep object detectors. In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 4560-4569, 2023.
• [22] Shepley A. J., Falzon G., Kwan P., and Brankovic L. Confluence: A robust noniou alternative to non-maxima suppression in object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10): 11561-11574, 2023.
• [23] Solovyev R., Wang W., and Gabruseva T. Weighted boxes fusion: Ensembling boxes from different object detection models. Image and Vision Computing, 107: 104117, 2021.
• [24] Varga L. A., Kiefer B., Messmer M., and Zell A. Seadronessee: A maritime benchmark for detecting humans in open water. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 2260-2270, 2022.
• [25] Wang C.-Y., Bochkovskiy A., and Liao H.-Y. M. YOLOv7: Trainable bag-offreebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7464-7475, 2023.
• [26] Wang W., Dai J., Chen Z., Huang Z., Li Z., Zhu X., Hu X., Lu T., Lu L., Li H., et al. InternImage: Exploring large-scale vision foundation models with deformable convolutions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14408-14419, 2023.
• [27] Xie X., Cheng G., Li Q., Miao S., Li K., and Han J. Fewer is more: Efficient object detection in large aerial images. arXiv preprint arXiv:2212.13136, 2022.
• [28] Xu J., Li Y., and Wang S. AdaZoom: adaptive zoom network for multi-scale object detection in large scenes. arXiv preprint arXiv:2106.10409, 2021.
• [29] Yang F., Fan H., Chu P., Blasch E., and Ling H. Clustered object detection in aerial images. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8311-8320, 2019.
• [30] Zhang T., Chen C., Liu Y., Geng X., Aly M. M. S., and Lin J. Psrrmaxpoolnms++: Fast non-maximum suppression with discretization and pooling. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1-15, 2024.
• [31] Zhou J., Vong C.-M., Liu Q., and Wang Z. Scale adaptive image cropping for uav object detection. Neurocomputing, 366:305-313, 2019.
• [32] Zong Z., Song G., and Liu Y. DETRs with collaborative hybrid assignments training. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6748-6758, 2023.