Infrared object detection using global and local cues based on LARK

Abstract Object detection has become a challenging problem in computer vision. Locally Adaptive Regression Kernel (LARK) based detection methods are able to produce visually pleasing results without any training. We in this paper present an effective object detection method by exploring global and local cues based on LARK features. First, we encode the local context similarity by exploiting region Structural LARK (SLARK) features, which measure the likeness of a pixel to its surroundings in the query image and the test image. Second, a global constraint based on SLARK features via Heat equation is learned to detect similar features in the test image. Results from matrix cosine similarity are computed to estimate similar regions between these computed features. A compactness score is provided to refine these regions. Next, we detect the location of objects in the test image using non-maxima suppression. We show in experiments that the proposed method significantly outperforms other methods on the infrared image datasets, localizing the objects in the test images effectively.

[1]  Jian Sun,et al.  Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Aykut Erdem,et al.  Structure-preserving image smoothing via region covariances , 2013, ACM Trans. Graph..

[3]  Patrick Pérez,et al.  View-Independent Action Recognition from Temporal Self-Similarities , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Antonio Torralba,et al.  Context models and out-of-context objects , 2012, Pattern Recognit. Lett..

[5]  Peyman Milanfar,et al.  Using local regression kernels for statistical object detection , 2008, 2008 15th IEEE International Conference on Image Processing.

[6]  Andrew Zisserman,et al.  Efficient retrieval of deformable shape classes using local self-similarities , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[7]  Zhixun Su,et al.  Diffuse visual attention for saliency detection , 2015, J. Electronic Imaging.

[8]  Yuting Zhang,et al.  Improving object detection with deep convolutional networks via Bayesian optimization and structured prediction , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Eli Shechtman,et al.  Matching Local Self-Similarities across Images and Videos , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Peyman Milanfar,et al.  Kernel Regression for Image Processing and Reconstruction , 2007, IEEE Transactions on Image Processing.

[11]  Frederic Devernay.  A Non-Maxima Suppression Method for Edge Detection with Sub-Pixel Accuracy , 1995 .

[12]  Fatih Murat Porikli,et al.  Region Covariance: A Fast Descriptor for Detection and Classification , 2006, ECCV.

[13]  Yi Zhang,et al.  Robust object detection based on local similar structure statistical matching , 2015 .

[14]  Peyman Milanfar,et al.  Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Shiguang Shan,et al.  Sigma Set: A small second order statistical region descriptor , 2009, CVPR.

[16]  Pietro Perona,et al.  Learning object categories from Google's image search , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[17]  Pietro Perona,et al.  Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[18]  Svetlana Lazebnik,et al.  Finding Things: Image Parsing with Regions and Per-Exemplar Detectors , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.