Ajay Raghavan

Detection of scene obstructions and persistent view changes in transportation camera systems

Unattended camera devices are increasingly being used in various intelligent transportation systems (ITS) for applications such as surveillance, toll collection, and photo enforcement. In these fielded systems, a variety of factors can cause camera obstructions and persistent view changes that may adversely affect their performance. Examples include camera misalignment, intentional blockage resulting from vandalism, and natural elements causing obstruction, such as foliage growing into the scene and ice forming on the porthole. In addition, other persistent view changes resulting from new scene elements of interest being captured, such as stalled cars, suspicious packages, etc. might warrant alarms. Since these systems are often unattended, it is often important to automatically detect such incidents early. In this paper, we describe innovative algorithms to address these problems. A novel approach that uses the image edge map to detect near-field obstructions without a reference image of the unobstructed scene is presented. A second algorithm that can be used to detect more generic obstructions and persistent view changes using a learned scene element cluster map is then discussed. Lastly, an approach to detect and distinguish persistent view changes from changes in the orientation of the fixed camera system is explained. Together, these algorithms can be useful in a variety of camera-based ITS.

Reference image-independent fault detection in transportation camera systems for nighttime scenes

Automated, unattended camera systems used for various transportation applications such as toll collection and photo enforcement need to capture high quality images in a variety of outdoor scenarios. In particular, they need to remain functional in low ambient illumination conditions (nighttime and cloudy day situations) to enable identification of objects or persons involved in incidents being monitored or extracting relevant information. Over time, for installed camera systems in the field, several problems can develop, such as external flash unit failures, focus drifts, and exposure issues. Thus, it is important to periodically monitor the nighttime images/videos taken by the camera system to ensure nominal functionality. However, due to constantly changing scene elements, it is not practical to compare a historical reference image with an identical scene against current camera output to detect problems. To address this, we present image quality metrics that can be extracted without a nominal reference image and can be used to characterize these problems. These can be incorporated into algorithms that can enable automated camera diagnostics for intelligent transportation systems.

Automated fault detection in violation enforcement cameras within Electronic Toll Collection systems

Electronic Toll Collection facilities offer travelers the ability to pay toll electronically, most commonly via Radio Frequency Identification (RFID) transponders placed within the vehicle. ETCs are complex systems comprising of a multitude of sensing and electronics equipment. To prevent violation, photo enforcement cameras are used to capture license plate images of the violating vehicle. To ensure adequate image quality and integrity of these cameras, it is standard maintenance practice to manually review camera images on a periodic basis. The manual review process can be expensive, error prone and may involve only a fraction of the images actually captured. To address this problem, we present algorithmic tools that can be used to automatically review images to detect any potential camera faults, thus, reduce human workload and increase maintenance efficiency. Wherever possible, we use no-reference or reduced-reference approaches for fault detection.

High-resolution, high-frequency wavelength shift detection of optical signals with low-cost, compact readouts

Fiber-optics (FO) have great potential for distributed sensing in various harsh environment applications. Their advantages include high resolution and multiplexing capabilities, inherent immunity to electromagnetic interference, and low weight/volume. However, their widespread adoption in commercial applications has been considerably limited by the high cost, size, weight, and lack of capabilities of the readout unit used to interpret the FO signals. PARC has developed a breakthrough wavelength shift detection (WSD) technology that is capable of reading out signals from wavelength-encoded FO and other optical sensors with high sensitivity using a compact, high-speed and low-cost unit. In this paper, its calibration and noise performance is demonstrated for high-resolution (up to 1,45 fm/√Hz) acoustic emission (AE) detection of fast (up to 1 MHz) dynamic strain signals.

Algorithm design for automated transportation photo enforcement camera image and video quality diagnostic check modules

Photo enforcement devices for traffic rules such as red lights, toll, stops, and speed limits are increasingly being deployed in cities and counties around the world to ensure smooth traffic flow and public safety. These are typically unattended fielded systems, and so it is important to periodically check them for potential image/video quality problems that might interfere with their intended functionality. There is interest in automating such checks to reduce the operational overhead and human error involved in manually checking large camera device fleets. Examples of problems affecting such camera devices include exposure issues, focus drifts, obstructions, misalignment, download errors, and motion blur. Furthermore, in some cases, in addition to the sub-algorithms for individual problems, one also has to carefully design the overall algorithm and logic to check for and accurately classifying these individual problems. Some of these issues can occur in tandem or have the potential to be confused for each other by automated algorithms. Examples include camera misalignment that can cause some scene elements to go out of focus for wide-area scenes or download errors that can be misinterpreted as an obstruction. Therefore, the sequence in which the sub-algorithms are utilized is also important. This paper presents an overview of these problems along with no-reference and reduced reference image and video quality solutions to detect and classify such faults.