Achint Setia

Achint Setia

Bengaluru, Karnataka, India
3K followers 500+ connections

Services

Articles by Achint

Activity

Join now to see all activity

Experience

Education

Publications

  • Co-operative Pedestrians Group Tracking in Crowded Scenes using an MST Approach

    IEEE Winter Conference on Applications of Computer Vision

    The problem of multiple pedestrian tracking in crowded scenes in videos recorded by a static uncalibrated camera is presented in this project. We propose an online multiple pedestrian
    tracking algorithm that utilizes group behaviour of pedestrians using minimum spanning trees (MST). We first divide pedestrians into several groups using the agglomerative hierarchical clustering, taking position and velocity of pedestrians as features, and then we track each group, represented
    by an MST…

    The problem of multiple pedestrian tracking in crowded scenes in videos recorded by a static uncalibrated camera is presented in this project. We propose an online multiple pedestrian
    tracking algorithm that utilizes group behaviour of pedestrians using minimum spanning trees (MST). We first divide pedestrians into several groups using the agglomerative hierarchical clustering, taking position and velocity of pedestrians as features, and then we track each group, represented
    by an MST, with the pictorial structures method. We also propose: (1) a method to detect and handle inter-pedestrian occlusions using a custom trained head detector for crowded scenes, and (2) an efficient method to detect newly entered pedestrians in the frame with help of a background subtraction method. Finally, we present experiments on two challenging and publicly available datasets and show improvements on multiple object tracking accuracy (MOTA) over other methods

    Other authors
    • Anurag Mittal
    See publication
  • Revisiting Pose Estimation with Foreshortening Compensation and Color Information

    VisiGrapp 2014 (9th International Joint Conference on Computer Vision, Imaging, and Computer Graphics Theory and Applications, Lisbon, Portugal 2014

    This paper addresses the problem of upper body pose estimation. The task is to detect and estimate 2D human configuration in static images for six parts: head, torso, and left-right upper and lower arms. The common approach to solve this has been the Pictorial Structure method (Felzenszwalb and Huttenlocher, 2005). We present this as a graphical model inference problem and use the loopy belief propagation algorithm for inference. When a human appears in fronto-parallel plane, fixed size part…

    This paper addresses the problem of upper body pose estimation. The task is to detect and estimate 2D human configuration in static images for six parts: head, torso, and left-right upper and lower arms. The common approach to solve this has been the Pictorial Structure method (Felzenszwalb and Huttenlocher, 2005). We present this as a graphical model inference problem and use the loopy belief propagation algorithm for inference. When a human appears in fronto-parallel plane, fixed size part detectors are sufficient and give reliable detection. But when parts like lower and upper arms move out of the plane, we observe foreshortening and the part detectors become erroneous. We propose an approach that compensates foreshortening in the upper and lower arms, and effectively prunes the search state space of each part. Additionally, we introduce two extra pairwise constraints to exploit the color similarity information between parts during inference to get better localization of the upper and lower arms. Finally, we present experiments and results on two challenging datasets (Buffy and ETHZ Pascal), showing improvements on the lower arms accuracy and comparable results for other parts.

    Other authors
    • Anoop Katti
    • Anurag Mittal
    See publication

Courses

  • Convex Optimization

    -

  • Digital Image Processing

    -

  • Digital Video Processing

    -

  • Graph Theory and Algorithms

    -

  • Hadoop and Map Reduce for Data Processing

    -

  • Machine Learning

    -

  • Natural Language Processing

    -

  • Pattern Recognition

    -

  • Probabilistic Graphical Models

    -

Projects

  • pikChat

    A chatbot where the user can chat with the bot, a bot with a display picture. The chatbot chats with you automatically responding relevant to your messages, using natural langauage processing and generation. Also, the facial expression of the display picture changes depending on the course the conversation takes. The user can create his own bot, just by uploading his phto. The NLP algorithms detect the change in emotion, and it is reflected in the image using morphing. A natural language…

    A chatbot where the user can chat with the bot, a bot with a display picture. The chatbot chats with you automatically responding relevant to your messages, using natural langauage processing and generation. Also, the facial expression of the display picture changes depending on the course the conversation takes. The user can create his own bot, just by uploading his phto. The NLP algorithms detect the change in emotion, and it is reflected in the image using morphing. A natural language generation system generated proper responses for the conversation.

    Other creators
    See project
  • Multiple Pedestrian Tracking in Severe Crowded Environment

    -

    The problem of multiple pedestrian tracking in crowded scenes in videos recorded by a static uncalibrated camera is presented in this project. We propose an online multiple pedestrian
    tracking algorithm that utilizes group behaviour of pedestrians using minimum spanning trees (MST). We first divide pedestrians into several groups using the agglomerative hierarchical clustering, taking position and velocity of pedestrians as features, and then we track each group, represented
    by an MST…

    The problem of multiple pedestrian tracking in crowded scenes in videos recorded by a static uncalibrated camera is presented in this project. We propose an online multiple pedestrian
    tracking algorithm that utilizes group behaviour of pedestrians using minimum spanning trees (MST). We first divide pedestrians into several groups using the agglomerative hierarchical clustering, taking position and velocity of pedestrians as features, and then we track each group, represented
    by an MST, with the pictorial structures method. We also propose: (1) a method to detect and handle inter-pedestrian occlusions using a custom trained head detector for crowded scenes, and (2) an efficient method to detect newly entered pedestrians in the frame with help of a background subtraction method. Finally, we present experiments on two challenging and publicly available datasets and show improvements on multiple object tracking accuracy (MOTA) over other methods

  • Beat Detection in Drumless Audio Signals

    -

    A CASA Model to track beats at three rhythmic levels; the quarter-note level, the half-note level,& the measure level.

    Other creators

Honors & Awards

  • Best Project at Summer Workshop on Computer Vision

    Computer Science and Engineering Dept., IIT Delhi

Languages

  • English

    Native or bilingual proficiency

  • Hindi

    Native or bilingual proficiency

  • French

    Elementary proficiency

Recommendations received

More activity by Achint

View Achint’s full profile

  • See who you know in common
  • Get introduced
  • Contact Achint directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Achint Setia

Add new skills with these courses