Research / Specializations / CSE - Specialization I

Specialization : Image Processing and Computer Vision

Digital image processing is the use of computer algorithms to perform image processing on digital images. It allows a much wider range of algorithms to be applied to the input data and can avoid problems such as the build-up of noise and signal distortion during processing. Computer vision is an interdisciplinary field that deals with how computers can be made for gaining high-level understanding from digital images or videos. From the perspective of engineering, it seeks to automate tasks that the human visual system can do. Computer vision tasks include methods for acquiring, processing, analyzing and understanding digital images. 
The research in this area is focussed on image processing and computer vision,  vision and machine learning, mathematical modelling and analysis of images, low level image processing algorithms, medical image analysis and processing, design and development of computer aided diagnostic systems (CAD), medical image reconstruction, features extraction and selection, pattern recognition and classification,  soft computing, video surveillance, biometrics, video processing, image forensics, and gait recognition.

Sub Areas under Computer Vision:

  • Image Processing, Computer Vision
  • AI, Machine learning and Deep Learning
  • Medical image analysis and Computer Aided Diagnostic Systems
  • Low level Image analysis
  • Pattern recognition, Pattern Classification, Soft Computing
  • Video Surveillance, Human Activity Recognition, Crowd Management
  • Biometrics
  • Digital Forensics and Security

Faculty:

Recent Publications:

 

  1. Santosh Kumar Tripathy, Harsh Kostha, Rajeev Srivastava, “TS-MDA: Two-Stream Multiscale Deep Architecture for Crowd Behavior Prediction”, Multimedia Systems, Springer. (Publsihed, July 2022) (SCI IF: 1.935) https://doi.org/10.1007/s00530-022-00975-x
  2. Surya Kant Singh, Rajeev Srivastava, “CSA-Net: Deep Cross-complementary Self Attention  and Modality-Specific  Preservation for Saliency Detection”, Neural Processing Letters, Springer. (Published May’2022).        https://doi.org/10.1007/s11063-022-10875-w (SCI IF: 2.565)
  3. Singh, D., Srivastava, R. Multi-scale graph-transformer network for trajectory prediction of the autonomous vehicles. Intel Serv Robotics, Vol. 15, pp. 307–320 (2022). https://doi.org/10.1007/s11370-022-00422-w  (Impact Factor -2.246) (Published: May 2022 )
  4. Surya Kant Singh and Rajeev Srivastava, ``A robust RGBD saliency method with improved probabilistic contrast and the global reference surface,'' The Visual Computer, Springer, 38 (3),  797–809, March’2022. https://doi.org/10.1007/s00371-020-02050-w (SCI-2.835)
  5. Tripathy, S.K., Sudhamsh, R., Srivastava, S. and Srivastava, R., MuST-POS: multiscale spatial-temporal 3D atrous-net and PCA guided OC-SVM for crowd panic detection. Journal of Intelligent & Fuzzy Systems, 42(4), pp. 3501-3516, March’ 2022. DOI: 10.3233/JIFS-211556. (SCI IF: 1.737)
  6. Divya Singh, Rajeev Srivastava, “Graph Neural Network with RNNs based Trajectory Prediction of Dynamic Agents for autonomous vehicle”, Applied Intelligence, Springer (Feb’2022)) (SCI IF: 5.019) https://doi.org/10.1007/s10489-021-03120-9
  7. Santosh Kumar Tripathy, Rajeev Srivastava, “AMS-CNN: Attentive Multi-Stream CNN for Video-based Crowd Counting”, International Journal of Multimedia Information Retrieval (MMIR), Springer, 10, 239–254 (Oct’2021). https://doi.org/10.1007/s13735-021-00220-7  (SCI IF: 3.205).
  8. Divya Singh, Rajeev Srivastava, “Channel spatial attention based single-shot object detector for autonomous vehicles”, Multimedia Tools and Applications, Springer, 81, pages 22289–22305 (2022) (Published online’ Sept’2021). https://doi.org/10.1007/s11042-021-11267-3   (SCI IF: 2.577)
  9. Divya Singh, Rajeev Srivastava, “An end to end trained hybrid CNN model for multi-object tracking”, Multimedia Tools and Applications, Springer. Multimedia Tools and Applications, Springer. (Published online, July 2022) https://doi.org/10.1007/s11042-021-11463-1  (SCI IF: 2.577)
  10. Divya Singh, Rajeev Srivastava, “Multi-scale graph-transformer network for trajectory prediction of the autonomous vehicles”, Intelligent Service Robotics, Springer, 15: 307–320 (May’2022). (SCI IF: 2.246). https://doi.org/10.1007/s11370-022-00422-w
  11. Ankit Kumar Jaiswal and Rajeev Srivastava, “Detection of Copy‑Move Forgery in Digital Image Using Multi‑scale, Multi‑stage Deep Learning Model”, 54, 75–100 (2022), Neural Processing Letters, Springer. https://doi.org/10.1007/s11063-021-10620-9 (SCI IF: 2.565)
  12. Pratistha Verma, Rajeev Srivastava, “Reconsideration of Multi-stage Deep Network for Human Pose Estimation”, Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, Taylor & Francis, 9 (6), 600-612 (April’ 2021).  https://doi.org/10.1080/21681163.2021.1902400  (CiteScore 4.2)
  13. Gargi Srivastava, Rajeev Srivastava, “Colon Tumour Localization using Three Input Variants to Faster R-CNN and Lazy Snapping”, International Journal of Imaging Systems and Technology, Wiley. 31 (4), 2123-2135, (Dec’ 2021) (SCI IF: 2.177). https://doi.org/10.1002/ima.22581
  14. Gargi Srivastava, Rajeev Srivastava, “Annotation of Images using Local Binary Pattern and Local Derivative Pattern after Salient Object Detection Using Minimum Directional Contrast and Gradient Vector Flow”, Signal, Image and Video Processing (SIVP-an International Journal), Springer. Vol. 15, pages 861–869 (2021). https://doi.org/10.1007/s11760-020-01807-z (SCI IF: 1.583).
  15. Ankit Jaiswal, Rajeev Srivastava, “Forensic Image Analysis using Inconsistent Noise Pattern”, Pattern Analysis and Applications (PAAA-an International Journal), Springer. Vol. 24, pages 655–667 (2021) https://doi.org/10.1007/s10044-020-00930-4  (SCI IF: 2.307).