Accurate Visual Odometry from a Rear Parking Camera (IV2011)

Steven Lovegrove, Andrew Davison and Javier Ibanez-Guzman (Renault S.A.S.)
Published at IV 2011.
Paper (PDF) | Slides (PDF)


As an increasing number of automatic safety and navigation features are added to modern vehicles, the crucial job of providing real-time localisation is predominantly performed by a single sensor, GPS, despite its well-known failings, particularly in urban environments. Various attempts have been made to supplement GPS to improve localisation performance, but these usually require additional specialised and expensive sensors. Offering increased value to vehicle OEMs, we show that it is possible to use just the video stream from a rear parking camera to produce smooth and locally accurate visual odometry in real-time. We use an efficient whole image alignment approach based on ESM, taking account of both the difficulties and advantages of the fact that a parking camera views only the road surface directly behind a vehicle.

Visual odometry is complementary to GPS in offering localisation information at 30Hz which is smooth and highly accurate locally whilst GPS is course but offers absolute measurements. We demonstrate our system in a large scale experiment covering real urban driving. We also present real-time fusion of our visual estimation with automotive GPS to generate a commodity-cost localisation solution which is smooth, accurate and drift free in global coordinates

Sample road texture from rear parking camera.

Four minute-long (left) / 10-second(right) sequences of integrated visual odometry (blue) against GPS only (red) and ground truth (green).

Fused visual odometry and GPS (blue) against GPS only (red) and ground truth (green). Overview (Left), Close-up (Right)


by Steven Lovegrove Jump to top