Filtered channel features for pedestrian detection

Zhang, Shanshan; Benenson, Rodrigo; Schiele, Bernt

doi:10.1109/cvpr.2015.7298784

Cited by 343 publications

(307 citation statements)

References 41 publications

Supporting

Mentioning

307

Contrasting

Order By: Relevance

“…14 CNN. CompACT-Deep [6] achieves the lowest miss rate (i.e., 11.70%) by combination of some local channel features (e.g., ACF [11], Checkboards [32], and LDCF [19]) and deep features (e.g., VGG [24]). Though CompACTDeep [6] has a better performance than NNNF-L4, the improvement of CompACT-Deep are based on very deep CNN model (i.e., VGG).…”

Section: Comparison With State-of-the-art Methods On Caltech Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry

Cao

Pang

2016

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

The discrimination and simplicity of features are very important for effective and efficient pedestrian detection. However, most state-of-the-art methods are unable to achieve good tradeoff between accuracy and efficiency. Inspired by some simple inherent attributes of pedestrians (i.e., appearance constancy and shape symmetry), we propose two new types of non-neighboring features (NNF): side-inner difference features (SIDF) and symmetrical similarity features (SSF). SIDF can characterize the difference between the background and pedestrian and the difference between the pedestrian contour and its inner part. SSF can capture the symmetrical similarity of pedestrian shape. However, it's difficult for neighboring features to have such above characterization abilities. Finally, we propose to combine both non-neighboring and neighboring features for pedestrian detection. It's found that nonneighboring features can further decrease the average miss rate by 4.44%. Experimental results on INRIA and Caltech pedestrian datasets demonstrate the effectiveness and efficiency of the proposed method. Compared to the state-ofthe-art methods without using CNN, our method achieves the best detection performance on Caltech, outperforming the second best method (i.e., Checkboards) by 1.63%.

show abstract

Section: Comparison With State-of-the-art Methods On Caltech Datasetmentioning

confidence: 99%

“…Aggregated Channel Features (ACF) [8], SquaresChnFtrs [3], InformedHaar [31], Locally Decorrelated Channel Features (LDCF) [19], and Checkboards [32] employ the same channel images as ICF. In ACF, the pixel sum of each block in each channel is computed and then the resulting lower resolution channels are smoothed [8,9].…”

Section: Related Workmentioning

confidence: 99%

Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry

Cao

Pang

2016

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…Recently, soft-cascade variants have demonstrated much superior detection performance [35,36,10,13] and are used in several applications, e.g., [27,29,18]. The softcascade thresholds are learned after the complete training of the strong classifier in a kind of calibration phase.…”

Section: Introductionmentioning

confidence: 99%

Soft-Cascade Learning with Explicit Computation Time Considerations

Barbosa-Anda

Lerasle

Briand

et al. 2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

This paper presents a novel framework for learning a soft-cascade detector with explicit computation time considerations. Classically, training techniques for softcascade detectors select a set of weak classifiers and their respective thresholds, solely to achieve the desired detection performance without any regard to the detector response time. Nevertheless, since computation time performance is of utmost importance in many time-constrained applications, this work divulges an optimization approach that aims to minimize the mean cascade response time, given a desired detection performance, fixed beforehand. The resulting problem is NP-Hard, therefore finding an optimal threshold vector can be very time-consuming, especially when building a soft-cascade detector of long length. An efficient local search procedure is presented that deals with long-length detectors. Our evaluations on two challenging public datasets confirm that a faster cascade detector can be learned while maintaining similar detection performances.

show abstract

“…Many solutions were already proposed in the literature. 25,[32][33][34][35][36] Despite the fact that deep convolutional neural network (DCNN) has pushed the state of the art of pedestrian detection, even the best trained generic detectors have poor performance when evaluating across datasets testing scenario. 37 This indicates that in some cases, the use of additional scene information can still be unavoidable.…”

Section: Human Detectionmentioning

confidence: 99%

A flexible human detection service suitable for Intelligent Spaces based on a multi-camera network

Almonfrey

Carmo

Queiroz

et al. 2018

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

The research field of the Intelligent Spaces has experienced increasing attention in the last decade. As an instance of the ubiquitous computing paradigm, the general idea is to extract information from the ambient and use it to interact and provide services to the actors present in the environment. The sensory analysis is mandatory in this area and humans are usually the principal actors involved. In this sense, we propose a human detector to be used in an Intelligent Space based on a multi-camera network. Our human detector is implemented in the same paradigm of our Intelligent Space. As a contribution of the present work, the human detector is designed to be a service that is scalable, reliable and parallelizable. It is also a concern of our service to be flexible, less structured as possible, attending different Intelligent Space applications and services, as well as their requirements. As it can be found in different everyday environments, a multicamera system is used to overcome some difficulties traditionally faced by existing human detection approaches. To validate our approach, we implement three different applications that are proof of concept of many day-to-day real tasks. Two of these applications involve human-robot interaction. With respect to time and detection performance requirements, our human detection service has proved to be suitable for interacting with the other services of our Intelligent Space, in order to successfully complete the tasks of each application.

show abstract

Filtered channel features for pedestrian detection

Cited by 343 publications

References 41 publications

Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry

Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry

Soft-Cascade Learning with Explicit Computation Time Considerations

A flexible human detection service suitable for Intelligent Spaces based on a multi-camera network

Contact Info

Product

Resources

About