The Computer Vision Laboratory at Tripura University (A Central University) was established on 12th June,2018 funded by Defence Research and Development Organisation (DRDO), DRDO Bhavan, New Delhi and has a short experience of security system and navigation. The research scholars have been working on that field for the last few days and also learning and gaining experience in this domain day by day.

1. One no of NVIDIA TITAN Xp graphics Card,with GPU Architecture Pascal,Frame Buffer 12 GB G5X,Memory Speed 11.4 Gbps,Boost Clock 1582 MHz.
2. One no of HP Z420 Workstation with 3.7 GHz speed.
3. Two no of PTZ High Resolution CCTV Cameras.
4. One no of Cloud Storage with 24TB HDD.
5. One 6 KVA Online UPS.
6. One 49 inch Panasonic Display Monitor.

The data are captured under two background conditions (i.e. static and dynamic background). For capturing the video with a static background, the camera is kept fixed with respect to the moving objects i.e. the background is static with respect to the moving objects. Conversely for dynamic background, the video is captured by mounting the camera on a moving vehicle (20∼30 km/h) where both the objects and background are moving simultaneously. The dataset contains 37 videos under static background condition and 18 videos under dynamic background condition.

Weather Challenges: The dataset includes urban scenes with buildings, trees, sky, vehicles and pedestrian with range from about 100 meters to about 5 kilometer so as to facilitate the observation of weather effects on scene appearances. The dataset contains 9 videos under poor illumination condition, 23 videos in foggy weather condition and 16 videos in dust condition.

Other Challenges: Beside these two major challenges, the dataset also contains scenes with multiple moving objects in single frame, overlapping of two moving objects in particular frame, camouflage or poorly textured moving objects and intermittent motions of objects. This subsets is very challenging and can be used to test benchmark algorithms in realistic scenarios.

Sample Images of Extended Tripura University Video Dataset

---

Tripura University Video Dataset at Night time (TU-VDN) Dataset

---

1. Sourav Dey Roy and Mrinal Kanti Bhowmik, "AWDMC-Net: Classification of Adversarial Weather Degraded Multiclass Scenes using a Convolution Neural Network", accepted in Computer Vision and Image Understanding, Elsevier, Indexed by Science Citation Index, Impact Factor: 3.876, Accepted on: 28^th June 2022.
2. Sourav Dey Roy and Mrinal Kanti Bhowmik, "Annotation and Benchmarking of a Video Dataset under Degraded Complex Atmospheric Conditions and Its Visibility Enhancement Analysis for Moving Object Detection", IEEE Transactions on Circuits and Systems for Video Technology, Indexed by Science Citation Index (SCI), Volume: 31, Issue: 3, pp. 844-862, Impact Factor: 4.133, Accepted on: 29^th April, 2020, DOI: 10.1109/TCSVT.2020.2991191.  Download
3. Anu Singha and Mrinal Kanti Bhowmik, "Salient Features for Moving Object Detection in Adverse Weather Conditions during Night Time", IEEE Transactions on Circuits and Systems for Video Technology, published by IEEE, Indexed by Science Citation Index (SCI), Impact Factor: 4.133, 2019.  Download
4. Anu Singha and Mrinal Kanti Bhowmik, "TU-VDN: Tripura University Video Dataset At Night Time In Degraded Atmospheric Outdoor Conditions For Moving Object Detection", Proceedings of 26th IEEE International Conference on Image Processing (ICIP) - Tier 2 Conference, pp. 2936-2940, 2019, Taipei, Taiwan.  Download
5. Sourav Dey Roy Mrinal Kanti Bhowmik, John Oakley, "A Ground Truth Annotated Video Dataset for Moving Object Detection in Degraded Atmospheric Outdoor Scenes", Proceedings of  25th IEEE International Conference on Image Processing (ICIP) - Tier 2 Conference, Athens, Greece, pp. 1318-1322. IEEE, 2018, Electronic ISSN: 2381-8549.  Download

Ongoing Project of Defence Research Organisation (DRDO), Govt. of India.