4,122 Hits in 5.0 sec

A Robust Hand Recognition In Varying Illumination [chapter]

Yoo-Joo Choi, Je-Sung Lee, We-Duke Cho
2008 Advances in Human Computer Interaction  
This section introduces a background subtraction method based on hue and hue-gradient.  ...  The introduced method constructs the background model based on the hue and the hue-gradient, and then robustly extracts the object contours from images obtained from a fixed camera by  ... 
doi:10.5772/5938 fatcat:ocz77gy2jzdvpefiob3fqdwtqy

Robust Local Descriptor for Color Object Recognition

Rabah Hamdini, Nacira Diffellah, Abderrahmane Namane
2019 Traitement du signal  
This approach is based on the combination of Gray-Edge color constancy, hue components in HSV (hue, saturation, value) color space and cell and bin ideas used in the HOG (Histograms of Gradients) descriptors  ...  Image category recognition is important to access visual information on the level of objects and scene types.  ...  This paper is organized as follows: In Section 2, we present some old color based feature extraction studies (histogram of oriented gradient (HOG), opponent histogram, hue histogram, SIFT (Scale Invariant  ... 
doi:10.18280/ts.360601 fatcat:uvcwybogbvbjzc2ftqh5fctk7q

Integrating Color and Gradient into Real-Time Curve Tracking and Feature Extraction for Video Surveillance [chapter]

Huiqiong Chen, Qigang Gao
2011 Video Surveillance  
Each moving object can be perceptually described by the GETs and CPPs extracted by the GET tracker.  ...  Fig. 9 . 9 Video surveillance system: GET maps and perceptual features of moving objects detected by the color-based tracker.  ...  Integrating Color and Gradient into Real-Time Curve Tracking and Feature Extraction for Video Surveillance, Video Surveillance, Prof.  ... 
doi:10.5772/15794 fatcat:zkueksfcuzaonmcuukxbrrzdea

Imprecise computations

J.W.S. Liu, Wei-Kuan Shih, Kwei-Jay Lin, R. Bettati, Jen-Yao Chung
1994 Proceedings of the IEEE  
Shadow points are often misclassified as object points causing errors in localization, segmentation, tracking and classification of moving vehicles.  ...  Shadow detection is critical for robust and reliable vision-based systems for traffic vision analysis.  ...  Acknowledgments The research is sponsored by National Hi-Tech Program of China (No. 2004AA114010) and National Science Foundation of China (No. 60473043).  ... 
doi:10.1109/5.259428 fatcat:ljnqd2oinfhv3muueu46uw2i7y

Nonlinear Color Space and Spatiotemporal MRF for Hierarchical Segmentation of Face Features in Video

M. Lievin, F. Luthon
2004 IEEE Transactions on Image Processing  
This paper deals with the low-level joint processing of color and motion for robust face analysis within a feature-based approach.  ...  A hierarchical segmentation scheme is based on Markov random field modeling, that combines hue and motion detection within a spatiotemporal neighborhood.  ...  Active contours are usually applied on the image intensity gradient in order to extract edge points on face features.  ... 
doi:10.1109/tip.2003.818013 pmid:15376958 fatcat:s52btbdfijh2timrgz4xiskxaa

Color Based Object Categorization Using Histograms of Oriented Hue and Saturation

Rabah Hamdini, Nacira Diffellah, Abderrahmane Namane
2021 Traitement du signal  
In this paper, we propose a new revolutionary approach for object categorization based on combining the HOG (Histograms of Oriented Gradients) descriptors with our two new descriptors, HOH (Histograms  ...  of Oriented Hue) and HOS (Histograms of Oriented Saturation), designed it in the HSL (Hue, Saturation and Luminance) color space and inspired by this famous HOG descriptor.  ...  Research and Technological Development of the Algerian Republic in general, without missing also to thank the SET laboratory of Blida 01 University.  ... 
doi:10.18280/ts.380504 fatcat:csypaq35jbaazdq3xkagr5ec54

Continuously Adaptive Mean-shift Tracking Algorithm Based on Improved Gaussian Model

Jinping Sun, School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221008, China, Enjie Ding, Dan Li, Kailiang Zhang, Ximin Wang
2020 Journal of Engineering Science and Technology Review  
The histograms of the hue component were respectively established in the foreground and background of the target area.  ...  To improve the accuracy of the traditional continuously adaptive mean-shift algorithm (CAMShift) in complex scenarios, a target tracking algorithm based on an improved Gaussian mixture model was proposed  ...  If the learning constant is too small, the background extraction time increases. The learning constant increases and is greater when the object is moving fast than when movement is slow.  ... 
doi:10.25103/jestr.135.07 fatcat:74xfixqbmvaspiti2oc6g3kyzy

Rainbow Flash Camera: Depth Edge Extraction Using Complementary Colors

Yuichi Taguchi
2014 International Journal of Computer Vision  
Since complementary colors are arranged at any position and its antipole on the ring, shadow regions where a half of the hue circle is occluded are colorized according to the orientations of depth edges  ...  Since complementary colors are arranged at any position and its antipole on the ring, shadow regions where a half of the hue circle is occluded are colorized according to the orientations of depth edges  ...  Marks, Ming-Yu Liu, Makito Seki, and Yukiyasu Domae for their feedback and support, and the anonymous reviewers of ECCV 2012 and this journal submission for their helpful comments.  ... 
doi:10.1007/s11263-014-0726-4 fatcat:nvh7ymbsezf5xan36w4rkwklg4

Wavelet Multi-Scale Transform Based Foreground Segmentation and Shadow Elimination~!2008-10-11~!2008-10-30~!2008-11-28~!

Ye-Peng Guan
2008 Open Signal Processing Journal  
The reference image is used to extract foreground no matter the objects enter the field of view before captured or not.  ...  An algorithm using wavelet multi-scale transform for segmenting foreground moving objects and suppressing shadow is proposed.  ...  In this paper, we use wavelet multi-scale transform based background subtraction to extract foreground moving objects.  ... 
doi:10.2174/1876825300801010001 fatcat:hkvev5cwqbcy5pzuiu6pajnn5e

An Effective Framework Using Region Merging and Learning Machine for Shadow Detection and Removal

Mohan kumar Shilpa , Et. al.
2021 Turkish Journal of Computer and Mathematics Education  
Moving cast shadows of moving objects significantly degrade the performance of many high-level computer vision applications such as object tracking, object classification, behavior recognition and scene  ...  According to the characteristics of shadow in HSV space and texture feature, the shadow is detected and removed to eliminate the shadow interference for the subsequent processing of moving targets.  ...  The method requires a small amount of computational time to detect the presence of moving objects for indoor video surveillance and is based on geometry features.  ... 
doi:10.17762/turcomat.v12i2.2098 fatcat:u5fgc7gntbflronkhf254kzjcq

Color-Aware Local Spatiotemporal Features for Action Recognition [chapter]

Fillipe Souza, Eduardo Valle, Guillermo Chávez, Arnaldo de A. Araújo
2011 Lecture Notes in Computer Science  
However, color has been proved an important element to the success of automated recognition of objects and scenes.  ...  We compare the performance of our color-aware version of STIP (which we have called HueSTIP) with the original one.  ...  We would like to thank CNPq, CAPES, FAPEMIG and FAPESP, Brazilian agencies, for the financial support to this work.  ... 
doi:10.1007/978-3-642-25085-9_29 fatcat:cclj44d2srfxjnytwq534fvofy

Robust Video Target Tracking Based on Multi-feature Fusion and H∞ Filtering

Howard Wang, Sing Kiong Nguang
2016 International Journal of Computer and Communication Engineering  
A robust video target motion state estimation method based on H∞ filtering is presented to recursively estimate and predict the target state which can narrow the scope of features searching and then greatly  ...  We extract color spatial distribution feature, target contour feature and edge gradient histogram of video targets, and calculate the matching degree between the candidate feature and target feature.  ...  Acknowledgment The authors would like to appreciate Liang Huang and Kevin Wang. References  ... 
doi:10.17706/ijcce.2016.5.2.79-98 fatcat:fm6ddevuyrfr5n44g7mwuwrkm4

Real Time Vehicle Tracking Algorithm Based on Statistical Characteristics in HSI Color Model

Pramod Sethy, Gaurav Singh, Karuna Lochab
2017 International Journal of u- and e- Service, Science and Technology  
The algorithm provides good results on our database, and it is relatively robust to variations in the luminance conditions and varied kinds of vehicles in different complex environment.  ...  On any horizontal slice through the model space, the hue (or "color" of the color) varies through the slice, and the saturation value (the purity of the color) increases radially outwards from the central  ...  It works on one connected component at a time and can move all over the image.  ... 
doi:10.14257/ijunesst.2017.10.1.06 fatcat:rbywmuvrzrbcdjphdy7j75kxiu

A Survey on Moving Object Tracking in Video

Barga Deori, Dalton Meitei Thounaojam
2014 International Journal on Information Theory  
The ongoing research on object tracking in video sequences has attracted many researchers.  ...  This paper proposes a literature review on the state of the art tracking methods, categorize them into different categories, and then identify useful tracking methods.  ...  For accurate and robust object contour tracking, they have extracted the contours with the help of region-based object contour extraction.  ... 
doi:10.5121/ijit.2014.3304 fatcat:kxmq4fhiebagvk644u7zxrlnpq

Abandoned Object Detection in Video-Surveillance: Survey and Comparison

Elena Luna, Juan San Miguel, Diego Ortego, José Martínez
2018 Sensors  
Such a dataset allows considering multiple and different scenarios, whereas presenting various challenges such as illumination changes, shadows, and a high density of moving objects, unlike existing literature  ...  We also build a multi-configuration system allowing one to select a range of alternatives for each stage with the objective of determining the combination achieving the best performance.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s18124290 fatcat:sktao7rg6jb77pymhqzniwrdfm
« Previous Showing results 1 — 15 out of 4,122 results