Face recognition (FR) and license plate recognition (LPR) are very crucial algorithms for identification of humans and vehicles in several applications such as surveillance, traffic and access-control. The advances in small single-board computers with high parallel processing power capabilities and the use of low-power Neural Processing Units (NPU) inside embedded System on Chips (SoC), enable real-time face detection (FD) and LPR at the edge. On the other hand, it is still a challenge to run multiple algorithms concurrently with high accuracy and prompt execution (high frame rates) that requires a very efficient software/video analytics algorithm development. Both FR and LPR algorithms need two-stage processing that involve detection and recognition. In this study, we propose a method that enables simultaneous face detection associated with landmark and quality information and LPR at the edge. The FD pipeline detects and tracks the faces, extracts landmarks and quality of faces, to select appropriate faces for recognition and then sends them to face recognition server. LPR algorithm consecutively performs detection and recognition on the embedded platform. Extended YOLO model is utilized for face selection while pruned YOLO and LPRNet models are exploited for license plate detection and license plate reading, respectively. In order to enable real-time performance with high accuracy; optimized AI-models and software architecture are used. As a result of this study, we obtain a high-performance, high-precision and real-time combined face/LPR recognition system which can be very useful for surveillance and security applications.
KEYWORDS: Cameras, Detection and tracking algorithms, Video surveillance, Video, Surveillance, Sensors, Image filtering, Target detection, System on a chip, Surveillance systems
Tracking with a Pan-Tilt-Zoom (PTZ) camera has been a research topic in computer vision for many years. Compared to tracking with a still fixed camera, the images captured with a PTZ camera are highly dynamic because the vision becomes difficult under some realistic conditions such as fast camera movements, occlusion and similar objects to the tracked target. Also, compensating for these problems is even more complex on edge system. With the increasing availability of small single-board computers with high parallel processing power capabilities, tracking objects using an onboard computer in real time has become feasible. Although these onboard computers allow a wide variety of computer vision methods to be executed, there is still a need to optimize these methods for running time and power consumption. This paper proposes a hybrid application with low CPU consumption for surveillance objects to detect and track at the edge. To detect the target at the beginning and in the case where the track has been lost, we use the deep learning based YOLOv3 model. This model provides one of the best trade-offs between speed and accuracy in the literature. A kernelized correlation filter is used to track the detected object in real-time. Combining these two algorithms provides high accuracy and speed even on onboard computers. Under a real-time streaming condition, the proposed method yields better results than the original KCF in tracking accuracy and outperforms a deep learning-based tracker when a target has a vast movement.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.