The Area Processing Unit of Caroline - Finding the Way through DARPA's Urban Challenge
نویسندگان
چکیده
This paper presents a vision-based color segmentation algorithm suitable for urban environments that separates an image into areas of drivable and non-drivable terrain. Assuming that a part of the image is known to be drivable terrain, other parts of the image are classified by comparing the Euclidean distance of each pixel’s color to the mean colors of the drivable area in real-time. Moving the search area depending on each frame’s result ensures temporal consistency and coherence. Furthermore, the algorithm classifies artifacts such as white and yellow lane markings and hard shadows as areas of unknown drivability. The algorithm was thoroughly tested on the autonomous vehicle ’Caroline’, which was a finalist in the 2007 DARPA Urban Challenge.
منابع مشابه
Urban and Architectural Development in Amman Downtown between Natural Disasters and Great Heritage Lose: Case Study
The center of Amman (Downtown) is one of the most marvelous sites in Jordan as it represents a wide range of heritage through time and space. However, the Downtown suffers from severe disorders in terms of negative urban development due to the cross cutting cultures between the past and present. Despite of its historical and cultural richness, several factors affected the architectural uniformi...
متن کاملHousing the Urban Poor in Nigeria through Community Participation Using Lessons from Nairobi Kenya
Migration of people to urban areas from the rural areas usually comes with its challenges interms of infrastructural requirement and housing to cater for growing population. One of the challenge for the urbandwellers in Nigeria is that of adequate housing. The inability of the government to meet this demand has seen thepeople concerned seeking alternative solutions to housing need. The resultin...
متن کاملپیشبینی رشد مکانی و توسعه پراکنده شهر ساری با بهکارگیری مدل سلولهای خودکار- مارکوف و شاخص آنتروپی شانون
Constant urban development in today’s world has turned urban growth management into a main challenge in the 21st century. Obtaining spatiotemporal information about the pattern and rate of urban growth is critical to a better understanding of the urban growth process and practicing appropriate management policies. The present study investigated the trend of urban sprawl in Sari, Iran. First, la...
متن کاملComparative Evaluation of Image Fusion Methods for Hyperspectral and Panchromatic Data Fusion in Agricultural and Urban Areas
Nowadays remote sensing plays a key role in the field of earth science studies due to some of the advantages, including data collection at a very low cost and time on a very large scale. Meanwhile, using hyperspectral data is of great importance due to the high spectral resolution. Because of some limitations, such as hyperspectral imaging technology, it suffers from a reduction in the spatial ...
متن کامل