A Fast-RCNN Implementation for Human Silhouette Detection in Video Sequences

The intention of this article is to implement a system of detection and segmentation of human silhouettes, the above mentioned tasks present a great challenge in security topics and innovation, in the last years and mainly on automated video surveillance systems, which require understanding the presence and human interaction in video sequences, e.g. Human Computer Interaction (HCI), Human Behaviour comprehension, Human fall detection, among others, but the most important is behavioural biometrics, this paper tackles the common step in these research areas: the Human silhouette extraction through the bounding box. To evaluate the proposed system, standardized databases where used and also proper videos are obtained trying to emulate real-world scenarios, where the quality and the distance are factors that have demonstrated challenges for the detection with computer vision and machine learning.

FPGA Implementation of Multi-scale Pedestrian Detection in Thermal Images

In this paper an embedded vision system for human silhouette detection in thermal images is presented. As the computing platform a reprogrammable device (FPGA – Field Programmable Gate Array) is used. The detection algorithm is based on a sliding window approach, which content is compared with a probabilistic template. Moreover, detection is four scales in supported. On the used test database, the proposed method obtained 97% accuracy, with average one false detection per frame. Due to the used parallelization and pipelining real-time processing for 720 × 480 @ 50 fps and 1280 × 720 @ 50 fps video streams was achieved. The system has been practically verified in a test setup with a thermal camera.

Hybrid Silhouette Detection for Real-Time Shadow Volume

In shadow volume, the most expensive computation is silhouette detection. In this paper, the triangular algorithm (TA) and visible-non-visible (VnV) algorithm that are famous algorithms to detect the outline of occluder are renewed. In this paper, we proposed a hybrid algorithm based on TA and VnV, namely Hybrid Silhouette Detection (HSD) algorithm. HSD is an improved algorithm that can recognize silhouette for generating real-time shadow volume. Our algorithm involves detecting silhouette and decreases the cost of implementation for shadow volume rendering. The last shadow volume algorithm using stencil buffer is rewritten and an algorithm for shadow volume using HSD with respect of culling invisible parts of scene is proposed. An accurate mathematical comparison between TA, VnV and HSD algorithms is undertaken. The obtained results confirm superiority of our proposed algorithm in terms of processing and rendering time. Our algorithm can be used in virtual environment to increase the frame