CMOS image sensor with a built-in lane detector

Pei Yung Hsiao*, Hsien Chein Cheng, Shih Shinh Huang, Li Chen Fu

*Corresponding author for this work

Research output: Contribution to journalJournal Article peer-review

4 Scopus citations

Abstract

This work develops a new current-mode mixed signal Complementary Metal-Oxide-Semiconductor (CMOS) imager, which can capture images and simultaneously produce vehicle lane maps. The adopted lane detection algorithm, which was modified to be compatible with hardware requirements, can achieve a high recognition rate of up to approximately 96% under various weather conditions. Instead of a Personal Computer (PC) based system or embedded platform system equipped with expensive high performance chip of Reduced Instruction Set Computer (RISC) or Digital Signal Processor (DSP), the proposed imager, without extra Analog to Digital Converter (ADC) circuits to transform signals, is a compact, lower cost key-component chip. It is also an innovative component device that can be integrated into intelligent automotive lane departure systems. The chip size is 2,191.4 × 2,389.8 μm, and the package uses 40 pin Dual-In-Package (DIP). The pixel cell size is 18.45 × 21.8 μm and the core size of photodiode is 12.45 × 9.6 μm; the resulting fill factor is 29.7%.

Original languageEnglish
Pages (from-to)1722-1737
Number of pages16
JournalSensors
Volume9
Issue number3
DOIs
StatePublished - 03 2009
Externally publishedYes

Keywords

  • CMOS
  • Current-mode
  • Gaussian filter
  • Image sensor
  • Intelligent transportation systems
  • Lane detection
  • Peak-finding algorithm
  • Photodiode

Fingerprint

Dive into the research topics of 'CMOS image sensor with a built-in lane detector'. Together they form a unique fingerprint.

Cite this