Avinash Sharma

Sushovan Chanda, Amogh Tiwari, Lokender Tiwari et al.

Recovering temporally consistent 3D human body pose, shape and motion from a monocular video is a challenging task due to (self-)occlusions, poor lighting conditions, complex articulated body poses, depth ambiguity, and limited availability of annotated data. Further, doing a simple perframe estimation is insufficient as it leads to jittery and implausible results. In this paper, we propose a novel method for temporally consistent motion estimation from a monocular video. Instead of using generic ResNet-like features, our method uses a body-aware feature representation and an independent per-frame pose and camera initialization over a temporal window followed by a novel spatio-temporal feature aggregation by using a combination of self-similarity and self-attention over the body-aware features and the perframe initialization. Together, they yield enhanced spatiotemporal context for every frame by considering remaining past and future frames. These features are used to predict the pose and shape parameters of the human body model, which are further refined using an LSTM. Experimental results on the publicly available benchmark data show that our method attains significantly lower acceleration error and outperforms the existing state-of-the-art methods over all key quantitative evaluation metrics, including complex scenarios like partial occlusion, complex poses and even relatively low illumination.

Avinash Sharma, Wally Niu, Christopher L. Hunt et al.

Adjusting to amputation can often time be difficult for the body. Post-surgery, amputees have to wait for up to several months before receiving a properly fitted prosthesis. In recent years, there has been a trend toward quantitative outcome measures. In this paper, we developed the augmented reality (AR) version of one such measure, the Prosthetic Hand Assessment Measure (PHAM). The AR version of the PHAM - HoloPHAM, offers amputees the advantage to train with pattern recognition, at their own time and convenience, pre- and post-prosthesis fitting. We provide a rigorous analysis of our system, focusing on its ability to simulate reach, grasp, and touch in AR. Similarity of motion joint dynamics for reach in physical and AR space were compared, with experiments conducted to illustrate how depth in AR is perceived. To show the effectiveness and validity of our system for prosthesis training, we conducted a 10-day study with able-bodied subjects (N = 3) to see the effect that training on the HoloPHAM had on other established functional outcome measures. A washout phase of 5 days was incorporated to observe the effect without training. Comparisons were made with standardized outcome metrics, along with the progression of kinematic variability over time. Statistically significant (p<0.05) improvements were observed between pre- and post-training stages. Our results show that AR can be an effective tool for prosthesis training with pattern recognition systems, fostering motor learning for reaching movement tasks, and paving the possibility of replacing physical training.

Avinash Sharma, Anurag Bhatnagar, Nikhar Tak et al.

In poly alphabetic substitution the plain texts letters are enciphered differently according to their position. The name poly alphabetic suggests that there are more than one key so we have used two keys combination instead of just one, in order to produce the cipher text. We can also use three or more keys to make the enciphering process more complicated. In this paper have produced ASCII Codes of the plain text and then we have reversed it said reverse ASCII Codes and then we have generated two keys K1 is generated by addition of reverse ASCII Codes and K2 is generated by addition of ASCII Codes. Then these K1 and K2 Keys are alternatively applied on Reverse ASCII codes in order to produce cipher text. On the Destination hand Deciphering is used to produce the plain text again. Our technique generates random cipher text for the same plain text and this is the major advantage of our technique.