Open Access. Powered by Scholars. Published by Universities.®
- Publication
Articles 1 - 5 of 5
Full-Text Articles in Engineering
Low-Cost Stereo Vision On An Fpga, Chris A. Murphy, Daniel Lindquist, Ann Marie Rynning, Thomas Cecil, Sarah Leavitt, Mark L. Chang
Low-Cost Stereo Vision On An Fpga, Chris A. Murphy, Daniel Lindquist, Ann Marie Rynning, Thomas Cecil, Sarah Leavitt, Mark L. Chang
Mark L. Chang
We present a low-cost stereo vision implementation suitable for use in autonomous vehicle applications and designed with agricultural applications in mind. This implementation utilizes the Census transform algorithm to calculate depth maps from a stereo pair of automotive-grade CMOS cameras. The final prototype utilizes commodity hardware, including a Xilinx Spartan-3 FPGA, to process 320times240 pixel images at greater than 150 frames per second and deliver them via a USB 2.0 interface.
Automated Least-Significant Bit Datapath Optimization For Fpgas, Mark L. Chang, Scott Hauck
Automated Least-Significant Bit Datapath Optimization For Fpgas, Mark L. Chang, Scott Hauck
Mark L. Chang
In this paper, we present a method for FPGA datapath precision optimization subject to user-defined area and error constraints. This work builds upon our previous research which presented a methodology for optimizing the dynamic range- the most significant bit position. In this work, we present an automated optimization technique for the least-significant bit position of circuit datapaths. We present results describing the effectiveness of our methods on typical signal and image processing kernels.
Interactionless Calendar-Based Training For 802.11 Localization, Mark Chang, Andrew J. Barry, Noah L. Tye
Interactionless Calendar-Based Training For 802.11 Localization, Mark Chang, Andrew J. Barry, Noah L. Tye
Mark L. Chang
This paper presents our work in solving one of the weakest links in 802.11-based indoor-localization: the training of ground-truth received signal strength data. While crowdsourcing this information has been demonstrated to be a viable alternative to the time consuming and accuracy-limited process of manual training, one of the chief drawbacks is the rate at which a system can be trained. We demonstrate an approach that utilizes users' calendar and appointment information to perform interactionless training of an 802.11-based indoor localization system. Our system automatically determines if a user attended a calendar event, resulting in accuracy comparable to our previously published …
Analysis Of Segmentation Algorithms For Pavement Distress Images, Allen Downey, Haris N. Koutsopoulos, Ibrahim El Sanhouri
Analysis Of Segmentation Algorithms For Pavement Distress Images, Allen Downey, Haris N. Koutsopoulos, Ibrahim El Sanhouri
Allen B. Downey
Collection and analysis of pavement distress data is an important component of any pavement‐management system. Various systems are currently under development that automate this process. They consist of appropriate hardware for the acquisition of pavement distress images and, in some cases, software for the analysis of the collected data. An important step in the automatic interpretation of images is segmentation, the process of extracting the objects of interest (distresses) from the background. We examine algorithms for segmenting pavement images and evaluate their effectiveness in separating the distresses from the background. The methods examined include the Otsu method, Kittler's method, a …
Primitive-Based Classification Of Pavement Cracking Images, Allen Downey
Primitive-Based Classification Of Pavement Cracking Images, Allen Downey
Allen B. Downey
Collection and analysis of pavement distress data are receiving attention for their potential to improve the quality of information on pavement condition. We present an approach for the automated classificaton of asphalt pavement distresses recorded on video or photographic film. Based on a model that describes the statistical properties of pavement images, we develop algorithms for image enhancement, segmentation, and distress classification. Image enhancement is based on subtraction of an “average” background: segmentation assigns one of four possible values to pixels based on their likelihood of belonging to the object. The classification approach proceeds in two steps: in the first …