en-us Tue, 5 Jun 2012 00:21:36 UTC Inmagic DB/Text WebPublisher http://114.111.144.247/ics-wpd/exec/icswppro.dll?AC=QUERY&TN=inroads&QY=find+RC+=+1205AR348E Mon, 14 May 2012 14:00:00 UTCThis research reviews and compares the possible wireless technologies that could possibly be installed along roadside for positioning purposes. Models and algorithms of integrating different positioning technologies are also presented. Various simulation schemes are designed to examine the performance benefits of united GNSS and roadside infrastructure for vehicle positioning. The results from these experimental studies have shown a number of useful findings. It is clear that in the open road environment where sufficient satellite signals can be obtained, the roadside wireless measurements contribute very little to the improvement of positioning accuracy at the sub-meter level, especially in the dual constellation cases. In the restricted outdoor environments where only a few GPS satellites, such as those with 45 elevations, can be received, the roadside distance measurements can help improve both positioning accuracy and availability to the sub-meter level. When the vehicle is travelling in tunnels with known heights of tunnel surfaces and roadside distance measurements, the sub-meter horizontal positioning accuracy is also achievable. Overall, simulation results have demonstrated that roadside infrastructure indeed has the potential to provide sub-meter vehicle position solutions for certain road safety applications if the properly deployed roadside measurements are obtainable. http://114.111.144.247/ics-wpd/exec/icswppro.dll?AC=QUERY&TN=inroads&QY=find+RC+=+1205AR014E Mon, 14 May 2012 14:00:00 UTC http://114.111.144.247/ics-wpd/exec/icswppro.dll?AC=QUERY&TN=inroads&QY=find+RC+=+1205AR039E Mon, 14 May 2012 14:00:00 UTC http://114.111.144.247/ics-wpd/exec/icswppro.dll?AC=QUERY&TN=inroads&QY=find+RC+=+1205AR047E Mon, 14 May 2012 14:00:00 UTC http://114.111.144.247/ics-wpd/exec/icswppro.dll?AC=QUERY&TN=inroads&QY=find+RC+=+1205AR197E Mon, 14 May 2012 14:00:00 UTCUnderstanding consumer needs is a high priority objective in new product development. The success in Vehicle-to-Vehicle (V2V) system design requires a balance of technical and marketing trade-offs. This paper aims to propose and discuss a choice modeling approach, to collect and model individuals’ perspectives and preferences, with respect to V2V-based in-vehicle information systems. Two empirical studies are presented and both display significant improvement in statistics when allowing for the heterogeneity across respondents. This study clearly demonstrates that product characteristics are critical decision variables that drive customer’s decisions in the context of a V2V system. The understanding of the population may not only have taste heterogeneity, but also behave based on diverse decision rules, should contribute to the innovative V2V development. The model also explores how variations cross individuals in the degree to which they engage with a stated choice survey. The findings offer further insights into the behavioral patterns of individuals in an evolving market. http://114.111.144.247/ics-wpd/exec/icswppro.dll?AC=QUERY&TN=inroads&QY=find+RC+=+1205AR349E Mon, 14 May 2012 14:00:00 UTCVehicle detection and tracking in road traffic surveillance is a classical task in computer vision and a critical component in a modern traffic monitoring system. However, most traditional systems are rendered ineffective in the face of three fundamental challenges inherent in visual object detection and tracking systems: occlusion, appearance variation and tracking failure. Compared to other object classes, the vehicle class exhibits more severe occlusions due to the low-angle low-height nature of road traffic surveillance cameras and the huge population of vehicle instances, and more appearance variation resulted from the high diversity of that population. The situation of tracking is no better owing to the complex environments in traffic scenes and the occlusion problem. This study explores two kinds of features, namely a vehicle-level feature - windshield, and a low-level feature - interest point. Both of the two features address the three challenges to some degree. Windshields observe less occlusions and a more uniform appearance than vehicles, and tracking is consequently easier; Interest point is a very stable and distinctive local image feature which is occlusion robust, and detection by grouping makes appearance variation irrelevant. Besides working independently, the heterogeneity of the two features also makes their collaboration beneficial. The semantic information of windshield provides guidance to the grouping of interest point, while the stability of interest point is an indispensable compensation to the failure modes of windshield. This study develops systems based on the individual features as well as the integration of features. It evaluates our systems on real world video sequences, and the results demonstrate the advantages of the proposed algorithms and their superior performances over the state-of-the-art methods.