Ajith Kuttannair Kumar

Color-Based Signal Light Tracking in Real-Time Video

Tracking or detecting the position and color of signal lights has an important role in transport industry. Auto detection of signal light colors and their position using computer vision techniques provides or acts as a proof against a fraudulent claim losses. The current technology, such as vehicle mounted recording system, provides event recognition videos and the cause behind an accident. But it does not provide the complete information about color associated with signal lights. The detection of the color of a signal light under different illuminations is a critical issue. In this research, an intelligent method for tracking color of signal lights using La*b* color model combined with contour tracking is proposed. This research finds application in transportation, law enforcement and insurance claims. The system increases the efficiency of the accident investigation process and reduces the economic loss associated with automobile accidents of all types.

Experimental investigation on switching characteristics of IGBTs for traction application

In traction application, inverters need to have high reliability on account of wide variation in operating conditions, extreme ambient conditions, thermal cycling and varying DC link voltage. Hence it is important to have a good knowledge of switching characteristics of the devices used. The focus of this paper is to investigate and compare switching characteristics and losses of IGBT modules for traction application. Dependence of device transition times and switching energy losses on dc link voltage, device current and operating temperature is studied experimentally.

An Efficient Video Enhancement Method Using LA*B* Analysis

In this paper, an efficient technique is proposed for real-time enhancement of video containing inconsistent and complex conditions like nonuniform and insufficient lighting. Beyond providing digital tools for video enhancement, this method provides a better approach to enhance a video in low lighting conditions without any loss of color information. This approach is based on histogram manipulations on La*b* color model of the video frame. This algorithm provides an effective way for video enhancement with simple computational procedures, which makes real-time enhancement for homeland security application successfully realized. Simulation is done on videos taken under bad lighting conditions and results are presented.

Development of the electromagnetic technology for broken rail detection from a mobil platform

Timely detection of breaks in running rails remains a topic of significant importance for the railroad industry. GE has been investigating new ideas of the Rail Integrity Monitoring or RIM technology that can be implemented on a wide range of the rolling stock platforms including locomotives, passenger and freight cars. The focus of the project is to establish a simple, non-contact, and inexpensive means of nondestructive inspection by fusion of known solutions with new technology development that can result in detection with high reliability. A scaled down model of a typical locomotive-track system has been developed at GE Global research for detailed study of the detection process. In addition, a finite element model has been established and used to understand distribution of the magnetic field and currents in such a system. Both models have been using the rails and wheel-axles geometry to establish a realistic model that would provide the electric current and magnetic field distribution close to the re...