다중 확률 맵을 이용한 향상된 Bounding Box 예측
Advanced Bounding Box Prediction With Multiple Probability Map
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we propose a bounding box prediction algorithm using multiple probability maps to improve object detection result of object detector. Although the performance of object detectors has been significantly improved, it is still not perfect due to technical problems and lack of learning data. Therefore, we use the result correction method to obtain more accurate object detection results. In the proposed algorithm, the preprocessed bounding box created as a result of object detection by the object detector is clustered in various form, and a conditional probability is given to each cluster to make multiple probability map. Finally, multiple probability map create new bounding box of object using morphological elements. Experiment results show that the newly predicted bounding box reduces the error in ground truth more than 45% on average compared to the previous bounding box.
Abstract
In this paper, we propose a bounding box prediction algorithm using multiple probability maps to improve object detection result of object detector. Although the performance of object detectors has been significantly improved, it is still not perfect due to technical problems and lack of learning data. Therefore, we use the result correction method to obtain more accurate object detection results. In the proposed algorithm, the preprocessed bounding box created as a result of object detection by the object detector is clustered in various form, and a conditional probability is given to each cluster to make multiple probability map. Finally, multiple probability map create new bounding box of object using morphological elements. Experiment results show that the newly predicted bounding box reduces the error in ground truth more than 45% on average compared to the previous bounding box.
참고문헌 (12)
- 장석우, "에이다부스트 알고리즘을 이용한 인체 영역의 강인한 검출", 한국산학기술학회논문지, 17(11), pp.403~409 (2016), 한국산학기술학회[DOI]
- Pedro F. Felzenszwalb, "Object Detection with Discriminatively Trained Part Based Models", IEEE Transaction on Pattern Analysis and Machine Intelligence, 32(9), pp.1627~1645 (2009)
- Joseph Redmon, "You Only Look Once: Unified, Real-Time Object Detection", Computer Vision and Pattern Recognition (CVPR) (2016)
- Y. Y. Boykov, "Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images", Proceedings of Internation Conference on Computer Vision, 1, pp.105~112 (2001)
- 박현준, "Octree 기반의 개선된 K-means 색상 양자화", 한국컴퓨터정보학회논문지, 20(12), pp.9~14 (2015), 한국컴퓨터정보학회
- Dawei Yang, "A Superpixel Segmentation Algorithm with Region Correlation Saliency Analysis for Video Pedestrian Detection", 36th Chinese Control Conference (CCC), pp.5396~5399 (2017)
- Brian Fulkerson, "Class segmentation and object localization with superpixel neighborhoods", IEEE 12th International Conference on Computer Vision, pp.670~677 (2009)
- Xiaodi Hou, "Saliency Detection: A Spectral Residual Approach", IEEE Conference on Computer Vision and Pattern Recognition, pp.1~8 (2007)
- Hiba Ramadan, "Pattern mining based video saliency detection", Intelligent Systems and Computer Vision (ISCV), pp.1~6 (2017)
- Xiaoou Tang, "Background Cut", ResearchGate, ~ (1970)
- 나이마 알람저, "지역 가중치 적용 퍼지 클러스터링을 이용한 효과적인 이미지", 한국컴퓨터정보학회논문지, 17(12), pp.83~93 (2012), 한국컴퓨터정보학회
- C. Rother, "GrabCut – Interactive Foreground Extraction using Iterated Graph Cuts", ACM Transactions on Graphics(SIGGRAPH’04), 23(3), pp.309~314 (2004)