FEATURE-ENHANCED CENTER NET FOR SMALL OBJECT DETECTION IN BIODEGRADABLE AND NON-BIODEGRADABLE AUTO SEGREGATION

Abstract

Small object detection is a critical task in the context of biodegradable and non-biodegradable waste segregation, where accurate identification and classification can significantly enhance automated waste management systems. This paper presents a novel approach called Feature-Enhanced CenterNet, which integrates advanced feature extraction techniques to improve the detection performance of small objects in cluttered and complex waste environments. By leveraging a robust backbone network combined with feature pyramid networks (FPN) and attention mechanisms, our method enhances the spatial resolution and contextual information of small object features, leading to more precise detections. Extensive experiments on a custom waste segregation dataset demonstrate the superiority of our Feature-Enhanced CenterNet over traditional detection models, particularly in identifying small-sized waste items. The proposed model achieves state-of-the-art performance in terms of both accuracy and efficiency, making it highly suitable for real-time waste sorting applications. The integration of this approach into automated waste management systems promises to streamline the segregation process, reduce human intervention, and promote sustainable waste-handling practices.

Keywords

CenterNet, biodegradable, non-biodegradable, segregation, FPN

References

Dai, J., Li, Y., He, K., & Sun, J. (2016). “R-FCN: Object Detection via Region-based Fully Convolutional Networks.” Advances in Neural Information Processing Systems (NeurIPS).

He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). “Mask R-CNN.” Proceedings of the IEEE International Conference on Computer Vision (ICCV).

Law, H., & Deng, J. (2018). “CornerNet: Detecting Objects as Paired Keypoints.” Proceedings of the European Conference on Computer Vision (ECCV).

Law, H., & Deng, J. (2018). “CornerNet-Lite: Efficient Keypoint Based Object Detection.” arXiv preprint arXiv:1904.08900.

Lin, T.-Y., & Maji, S. (2020). “HRNet: Deep High-Resolution Representation Learning for Visual Recognition.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). “Feature Pyramid Networks for Object Detection.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). “Focal Loss for Dense Object Detection.” Proceedings of the IEEE International Conference on Computer Vision (ICCV).

Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., … & Zitnick, C. L. (2014). “Microsoft COCO: Common Objects in Context.” arXiv preprint arXiv:1405.0312.

Liu, S., Huang, D., Wang, Y., Wang, L., & Tan, T. (2020). “CenterNet: Object Detection with Keypoint Triplets.” IEEE Transactions on Pattern Analysis and Machine Intelligence.

Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016). “SSD: Single Shot MultiBox Detector.” European Conference on Computer Vision (ECCV).

Redmon, J., & Farhadi, A. (2018). “YOLOv3: An Incremental Improvement.” arXiv preprint arXiv:1804.02767.

Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). “You Only Look Once: Unified, Real-Time Object Detection.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Ren, S., He, K., Girshick, R., & Sun, J. (2015). “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.” Advances in Neural Information Processing Systems (NeurIPS).

Wang, Y., Zhang, Z., Yang, Z., & Chen, Y. (2019). “Auto-Encoding Twin-Brother Networks for Object Tracking.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). “Learning Deep Features for Discriminative Localization.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

To cite this article

Ganesh, P. & Haridas, K. (2024). Feature-Enhanced Center Net for Small Object Detection in Biodegradable and Non-Biodegradable Auto Segregation. John Foundation Journal of EduSpark, 6(3), 16-27.