Rank Preserving Sparse Learning for Kinect Based Scene Classification

By Dapeng Tao, Lianwen Jin, Zhao Yang, Xuelong Li. 2013

48 citations recorded by the source corpus.

With the rapid development of the RGB-D sensors and the promptly growing population of the low-cost Microsoft Kinect sensor, scene classification, which is a hard, yet important, problem in computer vision, has gained a resurgence of interest recently. That is because the depth of information provided by the Kinect sensor opens an effective and innovative way for scene classification. In this paper, we propose a new scheme for scene classification, which applies locality-constrained linear coding (LLC) to local SIFT features for representing the RGB-D samples and classifies scenes through the cooperation between a new rank preserving sparse learning (RPSL) based dimension reduction and a simple classification method. RPSL considers four aspects: 1) it preserves the rank order information of the within-class samples in a local patch; 2) it maximizes the margin between the between-class samples on the local patch; 3) the L1-norm penalty is introduced to obtain the parsimony property; and 4) it models the classification error minimization by utilizing the least-squares error minimization. Experiments are conducted on the NYU Depth V1 dataset and demonstrate the robustness and effectiveness of RPSL for scene classification.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Jun Cheng
2. Dacheng Tao
3. Ling Shao
4. Bo Du
5. Qiqi Zhu
6. Dapeng Tao
7. Jungong Han
8. Lefei Zhang

In Computer Vision and Pattern Recognition

1. Liangpei Zhang
2. Bo Du
3. Dacheng Tao
4. Xuelong Li
5. Lefei Zhang
6. Ling Shao
7. Yanfei Zhong
8. Li Liu

Citations in the corpus

• RGB-D datasets using microsoft kinect or similar sensors: a survey (2016, methodology): “The representative research work using these two datasets as the benchmark for indoor segmentation and classification can be found in [77, 94, 95].”
• Scene Classification Based on the Multifeature Fusion Probabilistic Topic Model for High Spatial Resolution Remote Sensing Imagery (2015, background): “To date, it has been systematically studied in natural image analysis [8]–[10].”
• Saliency-Guided Unsupervised Feature Learning for Scene Classification (2015, background): “2) Dropout: Combining the predictions of many different models or classifiers is a very successful way to increase the test accuracy [32]–[34]; however, it is too expensive for the proposed framework as it would take several hours to train different networks which contain different feature extractor”
• Local structure preserving discriminative projections for RGB-D sensor-based scene classification (2015, background): “Feature representation is a hot topic in image classification [37,41,46,55,64].”
• Stacked Convolutional Denoising Auto-Encoders for Feature Representation (2017, methodology): “In our model, to make the learned features more discriminative, sparse constraint is included to the hidden representation [40], [41].”
• Block-Row Sparse Multiview Multilabel Learning for Image Classification (2016, background): “For example, the global feature HSV has been shown less robust to the changes in frame rate, video length, and captions, while the local feature SIFT is robust to them but sensitive to changes in contrast, brightness, scale, rotation, and camera viewpoint [18]–[22].”