TY - GEN
T1 - Automated Map Reading
T2 - Image Based Localisation in 2-D Maps Using Binary Semantic Descriptors
AU - Panphattarasap, Pilailuck
AU - Calway, Andrew
PY - 2019/3
Y1 - 2019/3
N2 - We describe a novel approach to image based lo- calisation in urban environments which uses semantic matching between images and a 2-D cartographic map. This contrasts with the majority of existing approaches which use image to image database matching. We use highly compact binary descriptors to represent locations, indicating the presence or not of semantic features, which significantly increases scalability and has the potential for greater invariance to variable imaging conditions. The approach is also more akin to human map reading, making it better suited to human-system interaction. In this initial study we use semantic features relating to buildings and road junctions in discrete viewing directions. CNN classi- fiers are used to detect the features in images and we match descriptor estimates with location tagged descriptors derived from the 2-D map to give localisation. The descriptors are not sufficiently discriminative on their own, but when concatenated sequentially along a route, their combination becomes highly distinctive and allows localisation even when using non-perfect classifiers. Performance is further improved by taking into account left or right turns over a route. Experimental results obtained using Google StreetView and OpenStreetMap data show that the approach has considerable potential, achieving localisation accuracy of around 85% using routes corresponding to approximately 200 meters.
AB - We describe a novel approach to image based lo- calisation in urban environments which uses semantic matching between images and a 2-D cartographic map. This contrasts with the majority of existing approaches which use image to image database matching. We use highly compact binary descriptors to represent locations, indicating the presence or not of semantic features, which significantly increases scalability and has the potential for greater invariance to variable imaging conditions. The approach is also more akin to human map reading, making it better suited to human-system interaction. In this initial study we use semantic features relating to buildings and road junctions in discrete viewing directions. CNN classi- fiers are used to detect the features in images and we match descriptor estimates with location tagged descriptors derived from the 2-D map to give localisation. The descriptors are not sufficiently discriminative on their own, but when concatenated sequentially along a route, their combination becomes highly distinctive and allows localisation even when using non-perfect classifiers. Performance is further improved by taking into account left or right turns over a route. Experimental results obtained using Google StreetView and OpenStreetMap data show that the approach has considerable potential, achieving localisation accuracy of around 85% using routes corresponding to approximately 200 meters.
KW - Localisation
KW - place recognition
KW - computer vision
KW - robotics
UR - http://www.scopus.com/inward/record.url?scp=85062999406&partnerID=8YFLogxK
U2 - 10.1109/IROS.2018.8594253
DO - 10.1109/IROS.2018.8594253
M3 - Conference Contribution (Conference Proceeding)
SN - 9781538680933
SP - 6341
EP - 6348
BT - 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)
PB - Institute of Electrical and Electronics Engineers (IEEE)
ER -