Passenger Compartment Violation Detection in HOV/HOT Lanes

Artan, Yusuf; Bulan, Orhan; Loce, Robert P.; Paul, Peter V.

doi:10.1109/tits.2015.2475721

Cited by 33 publications

(27 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object detection is one of the fundamental technologies for intelligent vision applications such as Advanced Driver Assistant Systems (ADAS), autonomous control in Unmanned Aerial Vehicles (UAV), mobile robot vision, surveillance systems and portable devices [1]- [5]. These applications and others require real-time processing and low power consumption.…”

Section: Introductionmentioning

confidence: 99%

A 58.6 mW 30 Frames/s Real-Time Programmable Multiobject Detection Accelerator With Deformable Parts Models on Full HD $1920\times 1080$ Videos

Suleiman

Zhang

Sze

2017

IEEE J. Solid-State Circuits

View full text Add to dashboard Cite

Abstract-This paper presents a programmable, energyefficient and real-time object detection hardware accelerator for low power and high throughput applications using deformable parts models, with 2× higher detection accuracy than traditional rigid body models. Three methods are used to address the high computational complexity of 8 deformable parts detection: classification pruning for 33× fewer part classification, vector quantization for 15× memory size reduction, and feature basis projection for 2× reduction in the cost of each classification. The chip was fabricated in a 65nm CMOS technology, and can process full high definition 1920×1080 videos at 60fps without any off-chip storage. The chip has two programmable classification engines for multi-object detection. At 30fps, the chip consumes only 58.6mW (0.94 nJ/pixel, 1168 GOPS/W). At a higher throughput of 60fps, the classification engines can be time multiplexed to detect even more than two object classes. This proposed accelerator enables object detection to be as energyefficient as video compression, which is found in most cameras today.

show abstract

Section: Introductionmentioning

confidence: 99%

A 58.6 mW 30 Frames/s Real-Time Programmable Multiobject Detection Accelerator With Deformable Parts Models on Full HD $1920\times 1080$ Videos

Suleiman

Zhang

Sze

2017

IEEE J. Solid-State Circuits

View full text Add to dashboard Cite

show abstract

“…If the regulations are strictly enforced, HOV/HOT lanes are typically less congested due to the constraints on the number of vehicle occupants. Enforcement of the rules of these lanes is currently performed by roadside enforcement officers using visual observation, which is known to be inefficient, costly, and potentially dangerous [1].…”

Section: Introductionmentioning

confidence: 99%

“…With the prevalence of video cameras in transportation imaging applications in the last two decades, several camera-based methods have been proposed to automate HOV/HOT lane enforcement [1,9,7,13]. While some of these techniques focus on vehicle occupancy detection using various face [9], empty seat [7] or skin detection [13] techniques, recent methods [1,16] have proposed image classification approaches to account for occlusion, especially for the images captured from side view.…”

Section: Introductionmentioning

confidence: 99%

“…While some of these techniques focus on vehicle occupancy detection using various face [9], empty seat [7] or skin detection [13] techniques, recent methods [1,16] have proposed image classification approaches to account for occlusion, especially for the images captured from side view.…”

Section: Introductionmentioning

confidence: 99%

“…We used the first site (domain C) as the source and the others (domains D and S) as target domains in our experiments. Our image acquisition system consisted of four submodules: a near-infrared (NIR) camera, camera triggers (i.e., induction loops, installed beneath the road as in red light enforcement systems, or laser break beam triggers [2]), an infrared (IR) illuminator and a processing unit [1]. The camera and illuminator are mounted along the road side to capture vehicle side-view images and see through the passenger rear-seat windows.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning architectures for domain adaptation in HOV/HOT lane enforcement

Wshah

Bulan

et al. 2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

Self Cite

View full text Add to dashboard Cite

High Occupancy Vehicle (HOV) and High Occupancy Tolling (HOT) lanes have been commonly practiced in several jurisdictions to reduce traffic congestion and promote car pooling. Camera-based methods have been recently proposed for a cost-efficient, safe and effective HOV/HOT lane enforcement with the prevalence of video cameras in transportation imaging applications. An important step in automated lane enforcement systems is classification of localized window/windshield images to distinguish passenger from no-passenger vehicles to identify violators. This can be performed using deep convolutional neural networks (CNNs), which are shown to significantly outperform hand-crafted features in several classification tasks. Training/fine-tuning CNNs require a set of passenger/nopassenger images manually labeled by an operator, which requires substantial time and effort that can result in excessive operational cost and overhead. In this paper, we study adaptability of three popular CNNs (i.e., AlexNet, VGG-M, and GoogLeNet) across different domains in classifying passenger/no-passenger images as part of an automated HOV/HOT lane enforcement system. Our experiments over 40, 000 side-view vehicle images show many interesting insights for domain adaptability of these deep learning architectures.

show abstract