Santanu Chaudhury

Bio: Santanu Chaudhury is an academic researcher from Indian Institute of Technology, Jodhpur. The author has contributed to research in topics: Ontology (information science) & Image segmentation. The author has an hindex of 28, co-authored 380 publications receiving 3691 citations. Previous affiliations of Santanu Chaudhury include Central Electronics Engineering Research Institute & Indian Institute of Technology Delhi.

A New Approach for Multi-Object Industrial Scene Analysis.

Abstract: A systertl h i ~ s e d toti a new a p p r o a c h f o r r e c o q t i i t i o t i #of p a r t i a l l y o b s c u r e d randoriily p o s i t i n n e d p l a n a r $ r ~ b. j e c t s i n a m c t l t i-o b j e c t s c e n e is p r e s e n t e d i t 1 t h i s p a p e r. The a p p r o a c h is b a s e d on a b d u c t i v e r e a s o n i n g. I n t e r p r e t a t ioti ,of t h e image i s q e t i e r a t e d frorii t h e o b s e r v e d s p a t i a l r e l a t i o n s between i n s t a n t i a t e d p r i m i t i v e s. The scheme i s g e n e r a l and r o b u s t enough t o accornodate u n c e r t a i n t i e s i n f e a t u r e and r e l a t i o n d e t e c t i o n. The a l g o r i t h n i is $ c a p a b l e o f recorqtilsitiq o b j e c t s w i t h riiitiiri~um o f s u p p o r t i v e e v i d e n c e. I n t r o d u c t i o n R e ~ o q t 7 l t l o t i of o c c l u d e d o b j e c t s is o f p r i m e …

View synthesis of scenes with multiple independently translating objects from uncalibrated views

Abstract: We propose a technique for view synthesis of scenes with static objects as well as objects that translate independent of the camera motion. Assuming the availability of three vanishing points in general position in the given views, we set up an affine coordinate system in which the static and moving points are reconstructed and the translations of the dynamic objects are recovered. We then describe how to synthesize new views corresponding to a completely new camera specified in the affine space with new translations for the dynamic objects. As the extent of the synthesized scene is restricted by the availability of corresponding points, we use a voxel-based volumetric scene reconstruction scheme to obtain a scene model and synthesize views of the entire scene. We present experimental results to validate our technique.

2-D to 3-D conversion of videos using fixed point learning approach

Abstract: The depth cues from multiple images are useful in accurate depth extraction while monocular cues from single still image are more versatile. In our paper, monocular cue which gives useful information about single frame and depth from motion using optical flow estimated from consecutive video frames are used to produce final depth maps. The machine learning approach is promising and new research direction in the field of depth estimation and thus 2-D to 3-D conversion. A fast automatic technique is proposed which utilizes a fixed point learning framework for the accurate estimation of depth maps of test images. For this task, a contextual prediction function is generated using training database of 2-D color and ground truth depth images. The depth maps obtained from monocular and motion depth cues of input video frames are used as input features for learning process. The depths generated from fixed point model are more accurate and reliable than MRF fusion of these depth cues. The stereo pairs are generated using depth maps predicted from fixed point learning. These final stereo pairs are converted to 3-D output video which is displayed on 3-DTV. For subjective evaluation, MOS score is calculated by showing final 3-D video to different viewers using 3-D glasses.

EG-SNIK: A Free Viewing Egocentric Gaze Dataset and Its Applications

Abstract: Egocentric vision data captures the first person perspective of a visual stimulus and helps study the gaze behavior in more natural contexts. In this work, we propose a new dataset collected in a free viewing style with an end-to-end data processing pipeline. A group of 25 participants provided their gaze information wearing Tobii Pro Glasses 2 set up at a museum. The gaze stream is post-processed for handling missing or incoherent information. The corresponding video stream is clipped into 20 videos corresponding to 20 museum exhibits and compensated for user’s unwanted head movements. Based on the velocity of directional shifts of the eye, the I-VT algorithm classifies the eye movements into either fixations or saccades. Representative scanpaths are built by generalizing multiple viewers’ gazing styles for all exhibits. Therefore, it is a dataset with both the individual gazing styles of many viewers and the generic trend followed by all of them towards a museum exhibit. The application of our dataset is demonstrated for characterizing the inherent gaze dynamics using state trajectory estimator based on ancestor sampling (STEAS) model in solving gaze data classification and retrieval problems. This dataset can also be used for addressing problems like segmentation, summarization using both conventional machine and deep learning approaches.

Inferring actor communities from videos

Abstract: In recent years there has been a growing interest in inferring social relations amongst actors in a video using audiovisual features, co-appearance features or both. The discovered relations between actors have been used for identifying leading roles, detecting rival communities in a movie plot etc. In this paper we propose an unsupervised method which uses the video’s transcript and closed caption information for discovering actor communities (group of actors or characters in a film that share a common perspective/viewpoint on an issue) from videos. The method proposed groups together actors using a topic model based approach, which jointly models actor-actor interaction (two actors interact when they share the same scene) and the topics associated with their conversations/dialogs. This joint modeling approach shows encouraging results compared to existing methods.

Data clustering: a review

Abstract: Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disciplines; this reflects its broad appeal and usefulness as one of the steps in exploratory data analysis. However, clustering is a difficult problem combinatorially, and differences in assumptions and contexts in different communities has made the transfer of useful generic concepts and methodologies slow to occur. This paper presents an overview of pattern clustering methods from a statistical pattern recognition perspective, with a goal of providing useful advice and references to fundamental concepts accessible to the broad community of clustering practitioners. We present a taxonomy of clustering techniques, and identify cross-cutting themes and recent advances. We also describe some important applications of clustering algorithms such as image segmentation, object recognition, and information retrieval.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Abstract: From the Publisher: The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Online and off-line handwriting recognition: a comprehensive survey

Abstract: Handwriting has continued to persist as a means of communication and recording information in day-to-day life even with the introduction of new technologies. Given its ubiquity in human transactions, machine recognition of handwriting has practical significance, as in reading handwritten notes in a PDA, in postal addresses on envelopes, in amounts in bank checks, in handwritten fields in forms, etc. This overview describes the nature of handwritten language, how it is transduced into electronic data, and the basic concepts behind written language recognition algorithms. Both the online case (which pertains to the availability of trajectory data during writing) and the off-line case (which pertains to scanned images) are considered. Algorithms for preprocessing, character and word recognition, and performance with practical systems are indicated. Other fields of application, like signature verification, writer authentification, handwriting learning tools are also considered.