Patents and Research

SKoPe3D is a unique synthetic vehicle keypoint dataset generated using the CARLA simulator from a roadside perspective. This comprehensive dataset includes generated images with bounding boxes, tracking IDs, and 33 keypoints for each vehicle. Spanning over 25k images across 28 scenes, SKoPe3D contains over 150k vehicle instances and 4.9 million keypoints.
Authors - Himanshu Pahadia, Duo Lu, Bharatesh Chakravarthi, Yezhou Yang

The patent proposes a novel system to capture the high-frequency vibrations produced as a result of muscle traction and visual feed to recognize and classify the hand gestures. It uses an ensemble neural network and performs tasks on the basis of recognized micro or macro-gestures. (Patent app no. - 201821049794)
Inventors - Himanshu Pahadia, Hardik Munjal, Anand Yashwanth

The patent proposes an architecture of a surveillance drone that is equipped will multiple environment mapping sensors. The drone follows the person and keeps track of any suspicious activity happening around the user he’s surveilling. A pretrained neural network can identify possible threats through a series of data. (Patent app no. - 201921023696)
Inventors - Hardik Munjal, Himanshu Pahadia

Patent proposes the architecture of a mixed reality headset with an egocentric camera that captures user’s daily activity which is later utilised to realise personal well-being, health tracking, fitness tracking and personal safety. MR enabled Headset helps the user visualise contextual information more seamlessly and effectively. (Filing in progress)
Inventors - Vidhi S. Rai, Himanshu Pahadia