Object detection is a vital component of modern video processing systems, and despite the availability of several efficient open-source feature-classifier frameworks and their corresponding implementation schemes, inclusion of this feature as a drop-in module in larger computer vision systems is still considered a daunting task. To this end, this work describes an open-source unified framework which can be used to train, test, and deploy an SVM-based object detector as a hardware-software co-design on FPGA using Simulink high-level synthesis tool. The proposed modular design can be seamlessly integrated within full systems developed using Simulink Computer Vision toolbox for rapid deployment. FPGA synthesis results show that the proposed hardware architecture utilizes fewer logic resources than the contemporary designs for similar operation. Moreover, experimental evidence has been provided to prove the generalization of the framework in efficiently detecting a variety of objects of interest including pedestrians, faces and traffic signs.
Invited: Bambu: an Open-Source Research Framework for the High-Level Synthesis of Complex Applications
