Creating robust high-throughput traffic sign detectors using centre-surround HOG statistics

Overett, Gary; Tychsen-Smith, Lachlan; Petersson, Lars; Pettersson, Niklas; Andersson, Lars

doi:10.1007/s00138-011-0393-1

Cited by 22 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work is the most similar to ours, but we are presenting results for more than 140 different classes of traffic signs (instead of 3 as in (Overett et al, 2011)) and show that some classes of signs are more difficult to detect than others. For example, blue squared signs are harder than red circles because of color-similarity with the sky and lack of easily distinguishable border.…”

Section: Related Worksupporting

confidence: 55%

“…It is also possible to take into account recognizer's confidence to filter out wrong detections. Similar requirement on false positive rate was also defined in (Overett et al, 2011).…”

Section: System Overviewmentioning

confidence: 99%

“…In (Overett et al, 2011) hardware-oriented implementation of HOG (Dalal et al, 2005) features allowed building a highthroughput system with 99% detection rate and 10 -10 false negatives rate per detector window. This work is the most similar to ours, but we are presenting results for more than 140 different classes of traffic signs (instead of 3 as in (Overett et al, 2011)) and show that some classes of signs are more difficult to detect than others.…”

Section: Related Workmentioning

confidence: 99%

“…As in (Baro et al, 2009), (Timofte et al, 2009) and (Overett et al, 2011) we use an attention cascade to make a detection problem tractable. First stages of our cascade consist of AdaBoost classifiers trained on dissociated dipoles features (Balas et al, 2003) that were also used in (Baro et al, 2009).…”

Section: Traffic Signs Detectionmentioning

confidence: 99%

See 3 more Smart Citations

A system for large-scale automatic traffic sign recognition and mapping

Chigorin

Konushin

2013

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:We present a system for the large-scale automatic traffic signs recognition and mapping and experimentally justify design choices made for different components of the system. Our system works with more than 140 different classes of traffic signs and does not require labor-intensive labelling of a large amount of training data due to the training on synthetically generated images. We evaluated our system on the large dataset of Russian traffic signs and made this dataset publically available to encourage future comparison.

show abstract

Section: Related Worksupporting

confidence: 55%

“…It is also possible to take into account recognizer's confidence to filter out wrong detections. Similar requirement on false positive rate was also defined in (Overett et al, 2011).…”

Section: System Overviewmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Traffic Signs Detectionmentioning

confidence: 99%

See 2 more Smart Citations

A system for large-scale automatic traffic sign recognition and mapping

Chigorin

Konushin

2013

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…For example (Z. Hu and Tsai 2011;Prisacariu et al 2010) characterize signs by combining edge and Haar-like features, and (Houben et al 2013;Mathias et al 2013;Overett et al 2014) leverages HOG features. More recent studies such as (Balali and Golparvar-Fard Using an integrated GPS/GIS field data logger to record and store inventory information (Caddell et al 2009;Jones 2004) Aerial/Satellite photography Analyzing high resolution images taken from aircraft or satellites to identify and extract highway inventory information (Veneziano et al 2002) (Balali and Golparvar-Fard 2014;Prisacariu et al 2010).…”

Section: Computer Vision Methods For Traffic Sign Detection and Classmentioning

confidence: 99%

Detection, classification, and mapping of U.S. traffic signs using google street view images for roadway inventory management

2015

View full text Add to dashboard Cite

Background: Maintaining an up-to-date record of the number, type, location, and condition of high-quantity low-cost roadway assets such as traffic signs is critical to transportation inventory management systems. While, databases such as Google Street View contain street-level images of all traffic signs and are updated regularly, their potential for creating an inventory databases has not been fully explored. The key benefit of such databases is that once traffic signs are detected, their geographic coordinates can also be derived and visualized within the same platform. Methods: By leveraging Google Street View images, this paper presents a new system for creating inventories of traffic signs. Using computer vision method, traffic signs are detected and classified into four categories of regulatory, warning, stop, and yield signs by processing images extracted from Google Street View API. Considering the discriminative classification scores from all images that see a sign, the most probable location of each traffic sign is derived and shown on the Google Maps using a dynamic heat map. A data card containing information about location and type of each detected traffic sign is also created. Finally, several data mining interfaces are introduced that allow for better management of the traffic sign inventories.

show abstract