Comparison Of Deep Object Detectors On A New Vulnerable Pedestrian Dataset

Pedestrian safety is one primary concern in autonomous driving. The under-representation of vulnerable groups in today's pedestrian datasets points to an urgent need for a dataset of vulnerable road users. In this paper, we first introduce a new vulnerable pedestrian detection dataset, BG Vulnerable Pedestrian (BGVP) dataset to help train well-rounded models and thus induce research to increase the efficacy of vulnerable pedestrian detection. The dataset includes four classes, i.e., Children Without Disability, Elderly without Disability, With Disability, and Non-Vulnerable. This dataset consists of images collected from the public domain and manually-annotated bounding boxes. In addition, on the proposed dataset, we have trained and tested five state-of-the-art object detection models, i.e., YOLOv4, YOLOv5, YOLOX, Faster R-CNN, and EfficientDet. Our results indicate that YOLOX and YOLOv4 perform the best on our dataset, YOLOv4 scoring 0.7999 and YOLOX scoring 0.7779 on the mAP 0.5 metric, while YOLOX outperforms YOLOv4 by 3.8 percent on the mAP 0.5:0.95 metric. Generally speaking, all five detectors do well predicting the With Disability class and perform poorly in the Elderly Without Disability class. YOLOX consistently outperforms all other detectors on the mAP (0.5:0.95) per class metric, obtaining 0.5644, 0.5242, 0.4781, and 0.6796 for Children Without Disability, Elderly Without Disability, Non-vulnerable, and With Disability, respectively. Our dataset and codes are available at https://github.com/devvansh1997/BGVP.

Combining Keystroke Dynamics and Face Recognition for User Verification

The massive explosion and ubiquity of computing devices and the outreach of the web have been the most defining events of the century so far. As more and more people gain access to the internet, traditional know-something and have-something authentication methods such as PINs and passwords are proving to be insufficient for prohibiting unauthorized access to increasingly personal data on the web. Therefore, the need of the hour is a user-verification system that is not only more reliable and secure, but also unobtrusive and minimalistic. Keystroke Dynamics is a novel Biometric Technique; it is not only unobtrusive, but also transparent and inexpensive. The fusion of keystroke dynamics and Face Recognition engenders the most desirable characteristics of a verification system. Our implementation uses Hidden Markov Models (HMM) for modelling the Keystroke Dynamics, with the help of two widely used Feature Vectors: Keypress Latency and Keypress Duration. On the other hand, Face Recognition makes use of the traditional Eigenfaces approach.The results show that the system has a high precision, with a False Acceptance Rate of 5.4% and a False Rejection Rate of 9.2%. Moreover, it is also future-proof, as the hardware requirements, i.e. camera and keyboard (physical or on-screen), have become an indispensable part of modern computing.