Autonomous driving is becoming one of the leading industrial research areas. Therefore many automobile companies are coming up with semi to fully autonomous driving solutions. Among these solutions, lane detection is one of the vital driver-assist features that play a crucial role in the decision-making process of the autonomous vehicle. A variety of solutions have been proposed to detect lanes on the road, which ranges from using hand-crafted features to the state-of-the-art end-to-end trainable deep learning architectures. Most of these architectures are trained in a traffic constrained environment. In this paper, we propose a novel solution to multi-lane detection, which outperforms state of the art methods in terms of both accuracy and speed. To achieve this, we also offer a dataset with a more intuitive labeling scheme as compared to other benchmark datasets. Using our approach, we are able to obtain a lane segmentation accuracy of 99.87% running at 54.53 fps (average).

Recently, as the light‐emitting diodes (LEDs) technology has improved, especially LED brightness is remarkable increased, the brightness of LCD panel is enough even if LED sources are located in only short edge sides (left and right) of the LCD module. As a result, the smart local dimming system is needed to use the invented LED back light unit (BLU) efficiently. In this paper, we proposed the new local dimming system to reduce power consumption and enhance motion picture quality for a new edge LED BLU. The proposed system is applied to active 2D local dimming algorithm and scanning technique at the same time. Our local dimming system has 3 advantages, 25% power saving, 1:100,000 contrast ratio and average MPRT 3.9ms with 240Hz panel. We verified performances by measurement. Finally, our 2D dimming technique was developed as AISC IP type which was merged in timing controller (TCON), so we can apply our system for mass product in 2011 year.

No abstract