الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 98 |  |  |
| | | from | 98 | | |
Abstract
Computer vision is considered a field of artificial intelligence (AI) that enables computers and systems to extract meaningful information from digital images, videos and any other visual inputs and take actions or make suggestions based on that information. If AI makes computers able to think, computer vision can also enable them to see, observe and understand.
Computer vision works probably the same as human vision, except humans have a head start. Human vision has lifelong training priorities depending on the situation, such as how a part objects are, how distant they are, whether they are moving and whether the image contains something wrong. Computer vision is widely used in industries ranging from energy and utilities to manufacturing and automotive driving assistance.
A Complete Computer vision system can be divided into two main categories: detection and classification. The Lane detection algorithm is a part of the computer vision detec- tion category and has been applied in autonomous driving and smart vehicle systems. The lane detection system is responsible for lane marking in a complex road environ- ment. At the same time, lane detection plays a crucial role in the warning system for a car when departs the lane. The implemented lane detection algorithm is mainly divided into two steps: edge detection and line detection.
Two lane detection hardware implementation solutions are developed and compared. One solution is implemented on a ZYNQ-7 ZC706 Evaluation Board FPGA and the other solution is implemented on Google Colab NVIDIA K80 Super GPU.
The latency, resource utilization, and power consumption for the accelerated portions of each system are compared and each system’s tradeoffs and use cases are considered.