Two-stage part-based pedestrian detection

Møgelmose, Andreas; Prioletti, Antonio; Trivedi, Mohan M.; Broggi, Alberto; Moeslund, Thomas B.

doi:10.1109/itsc.2012.6338898

Cited by 17 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HOG features with an SVM classifier, that are used in third stage of the cascaded system, verify detected objects as either vehicles or pedestrians. Using HOG with the SVM classifier as a verification step has some benefits like reducing false positives and system speed up [21]. The HOG classifiers were trained using a linear kernel with LIBSVM [22] to distinguish both vehicles and pedestrians from other objects.…”

Section: Datasetsmentioning

confidence: 99%

Contextual Combination of Appearance and Motion for Intersection Videos with Vehicles and Pedestrians

Shirazi

Morris

2014

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. Object detection and classification is challenging problem for vision-based intersection monitoring since traditional motion-based techniques work poorly when pedestrians or vehicles stop due to traffic signals. In this work, we present a method for vehicle and pedestrian recognition at intersections that benefits from both motion and appearance cues in video surveillance. Vehicle and pedestrian recognition performance is compared using motion, appearance and combined cues in contextually relevant stop areas to improve recognition. Experimental evaluation shows 5% average improvement for vehicle and pedestrian recognition at two Las Vegas intersections.

show abstract

Section: Datasetsmentioning

confidence: 99%

Contextual Combination of Appearance and Motion for Intersection Videos with Vehicles and Pedestrians

Shirazi

Morris

2014

Advances in Visual Computing

View full text Add to dashboard Cite

show abstract

“…Key statistics about the data sets are presented in Table I and also presented in [7]. While the INRIA data set was used in the first presentation of this system [9], this paper deals mainly with the DaimlerDB since that is a much larger data set created with focus on in-car detection systems. All testing is done against the DaimlerDB (see Section IV for further details), and we compare the training with the DaimlerDB and the INRIA data set.…”

Section: A Public Data Setsmentioning

confidence: 99%

“…Significant improvements were applied to the system described in [9], as shown in Fig. 6, by comparing the blue graph with the green graph.…”

Section: Key Improvementsmentioning

confidence: 99%

See 1 more Smart Citation

Part-Based Pedestrian Detection and Feature-Based Tracking for Driver Assistance: Real-Time, Robust Algorithms, and Evaluation

Prioletti

Møgelmose

Grisleri

et al. 2013

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

Abstract-Detecting pedestrians is still a challenging task for automotive vision systems due to the extreme variability of targets, lighting conditions, occlusion, and high-speed vehicle motion. Much research has been focused on this problem in the last ten years and detectors based on classifiers have gained a special place among the different approaches presented. This paper presents a state-of-the-art pedestrian detection system based on a two-stage classifier. Candidates are extracted with a Haar cascade classifier trained with the Daimler Detection Benchmark data set and then validated through a part-based histogram-of-orientedgradient (HOG) classifier with the aim of lowering the number of false positives. The surviving candidates are then filtered with feature-based tracking to enhance the recognition robustness and improve the results' stability. The system has been implemented on a prototype vehicle and offers high performance in terms of several metrics, such as detection rate, false positives per hour, and frame rate. The novelty of this system relies on the combination of a HOG part-based approach, tracking based on a specific optimized feature, and porting on a real prototype.

show abstract

“…The performance of classification of pedestrian with the help of Haar cascade detector and part based validation using HOG-SVM is implemented and analyzed. The part based pedestrian detection systems [9] build a robust validation of pedestrians compared to the other systems.…”

Section: Introductionmentioning

confidence: 99%

NIR image based pedestrian detection in night vision with cascade classification and validation

Govardhan

Pati

2014

2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies

View full text Add to dashboard Cite

Pedestrian detection is one of the vital issues in advanced driving assistance applications. It is even more important in nighttime. This paper presents a robust algorithm for a nighttime pedestrian detection system. A NIR (Near Infrared) camera is used in this system to take images of a night scene. As there are large intra class variations in the pedestrian poses, a tree structured classifier is proposed here to handle the problem by training it with different subset of images and different sizes. This paper discusses about combination of Haar- Cascade and HOG-SVM (Histogram of Oriented GradientsSupport Vector Machine) for classification and validation. HaarCascade is trained such that to classify the full body of humans which eliminates most of the non-pedestrian regions. For refining the pedestrians after detection, a part based SVM classifier with HOG features is used. Upper and lower body part HOG features of the pedestrians are used for part based validation of detected bounding boxes. A full body validation scheme is also implemented using HOG-SVM when any one of the part based validation does not validate that particular part. Combination of the different types of complementary features yields betterresults. Experiments on test images determines that the proposed pedestrian detection system has a high detection rate and low false alarm rate since it works on part based validation process.

show abstract

Two-stage part-based pedestrian detection

Cited by 17 publications

References 20 publications

Contextual Combination of Appearance and Motion for Intersection Videos with Vehicles and Pedestrians

Contextual Combination of Appearance and Motion for Intersection Videos with Vehicles and Pedestrians

Part-Based Pedestrian Detection and Feature-Based Tracking for Driver Assistance: Real-Time, Robust Algorithms, and Evaluation

NIR image based pedestrian detection in night vision with cascade classification and validation

Contact Info

Product

Resources

About