원문정보
초록
영어
Image holistic scene understanding based on image intrinsic characteristics and conditional random fields is proposed. The model integrates image scene classification, image semantic segmentation and object detection. 1) For the scene classification, we use method of PHOW feature extraction plus KPCA dimensional reduction to obtain feature information for each image. 2) For object detection section, saliency detection and segmentation characteristics of the image object detection is useful. We propose the method by integrating image segmentation information got by the method proposed in literature [1]. 3) For the semantic segmentation: (1) For the unary potentials, we incorporating HOG, RGB color histogram and LBP features by the methods proposed in literature [2]; (2) The image manifold structural features can better reflect the importance between hyper-pixel regions and eventually boost accuracy. Therefore, we add the higher-order potential item to reflect inherent manifold image feature of each super pixel region. The experiments testify that model performance has raised on all three sub-tasks.
목차
1. Introduction
2. Related Works
3. Our Holistic Scene Understanding Framework
4. Image Intrinsic Feature Fusion
4.1. Unary Potential Feature Information
4.2. Image Manifold Feature Information
4.3. Image Holistic Class Feature Information
4.4. Image Saliency Detection Information
5. Feature Engineering of Holistic Scene Understanding
5.1. Segmentation Potential
5.2. Scene Existence Potential
5.3. Object Detection Potential
5.4. Object Detection Potential
6. Experimental Design
6.1. Datasets
6.2. Experimental Platforms
6.3. Experimental Settings
7. Experimental Result and Analysis
7.1 Image Scene Classification
7.2 Image Semantic Segmentation
7.3 Object Detection
7.4 The Impact Analysis of Mask Size
8. Conclusion and future work
Acknowledgements
References