CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Pedestrian Detection using Augmented Training Data

Jonas Nilsson (Institutionen för signaler och system, Mekatronik) ; Patrik Andersson (Institutionen för signaler och system) ; Irene Y.H. Gu (Institutionen för signaler och system, Signalbehandling) ; Jonas Fredriksson (Institutionen för signaler och system, Mekatronik)
22th International Conference on Pattern Recognition, 24-28 Aug. 2014, Stockholm, Sweden (1051-4651). p. 4548-4553. (2014)
[Konferensbidrag, refereegranskat]

Detecting pedestrians is a challenging and widely explored problem in computer vision. Many approaches rely on large quantities of manually labelled training data to learn a pedestrian classifier. To reduce the need for collecting and manually labelling real image training data, this paper investigates the possibility to use augmented images to train a pedestrian classifier. Augmented images are generated by rendering virtual pedestrians onto real image backgrounds. Classifiers learned from real or augmented training data are evaluated on real image test data from the widely used Daimler Mono Pedestrian benchmark data set. Results show that augmented training data generated from a single 200 frame image sequence reach 70% average detection rate at one False Positives Per Image (FPPI), compared to 81% for a classifier trained by a large-scale real data set. Results also show that complementing real training data with augmented data improves detection performance, compared to using real training data only.

Nyckelord: Pedestrain detection, argumented data, SVMs, classification, detetion, vehicle safety

Den här publikationen ingår i följande styrkeområden:

Läs mer om Chalmers styrkeområden  

Denna post skapades 2014-05-16. Senast ändrad 2015-09-15.
CPL Pubid: 198151


Läs direkt!

Länk till annan sajt (kan kräva inloggning)