Adapting pedestrian detectors to new domains: A comprehensive review

Htike, Kyaw Kyaw; Hogg, David C.

doi:10.1016/j.engappai.2016.01.029

Cited by 12 publications

(9 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The detection methods based on deep learning are better in recognition performance. In summary, the detection efficiency of the derivatives of these methods is basically the same [28], but SVM is more concise than the AdaBoost, and the number of parameters is less than that of CNN.…”

Section: Proposed Methodsmentioning

confidence: 99%

Real‐time face recognition based on pre‐identification and multi‐scale classification

Min

Fan

et al. 2019

IET Computer Vision

View full text Add to dashboard Cite

In face recognition, searching a person's face in the whole picture is generally too time-consuming to ensure highdetection accuracy. Objects similar to the human face or multi-view faces in low-resolution images may result in the failure of face recognition. To alleviate the above problems, a real-time face recognition method based on pre-identification and multiscale classification is proposed in this study. The face area is segmented based on the proportion of human faces in the pedestrian area to reduce the search range, and faces can be robustly detected in complicated scenarios such as heads moving frequently or with large angles. To accurately recognise small-scale faces, the authors propose the multi-scale and multi-channel shallow convolution network, which combines a multi-scale mechanism on the feature map with a multi-channel convolution network for real-time face recognition. It performs face matching only in the pre-identified face areas instead of the whole image, therefore it is more efficient. Experimental results showed that the proposed real-time face recognition method detects and recognises faces correctly, and outperforms the existing methods in terms of effectiveness and efficiency.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Real‐time face recognition based on pre‐identification and multi‐scale classification

Min

Fan

et al. 2019

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…This is even more problematic when multiple classifiers must be trained to correspond to multiple settings of the simulation or of the environment. A linked example, albeit not in a simulation context, was presented by Htike and Hogg (2016), who considered the problem of training multiple, context-dependent, pedestrian detectors needed for autonomous cars. Among other solutions, they pointed toward Active Learning (AL) as a promising research direction.…”

Section: Introductionmentioning

confidence: 99%

Coupling digital simulation and machine learning metamodel through an active learning approach in Industry 4.0 context

Chabanet

El-Haouzi

Thomas

2021

Computers in Industry

View full text Add to dashboard Cite

Although digital simulations are becoming increasingly important in the industrial world owing to the transition toward Industry 4.0, as well as the development of digital twin technologies, they have become increasingly computationally intensive. Many authors have proposed the use of Machine Learning (ML) metamodels to alleviate this cost and take advantage of the enormous amount of data that are currently available in industry. In an industrial context, it is necessary to continuously train predictive models integrated into decision support systems to ensure the consistency of their prediction quality over time. This led the authors to investigate Active Learning (AL) concepts in the particular context of the sawmilling industry. In this paper, a method based on AL is proposed to combine simulation and an ML metamodel that is trained incrementally using only selected data (smart data). A case study based on the sawmilling industry and experiments are shown, the results of which prove the possible advantages of this approach.

show abstract

“…The adaptation of people detectors is therefore desired to successfully apply such detectors to unseen data [6]. This adaptation can be approached as best algorithm selection [7,8], domain adaptation for learning scene-specific detectors [9], data augmentation for the video-surveillance domain [10] and unsupervised feature learning [3,4]. However, these approaches imply retraining models for the new target domain, which may not be possible in certain applications such as real-time video-surveillance where data may not be available in advance.…”

Section: Introductionmentioning

confidence: 99%

Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information †

García-Martín

SanMiguel

Martínez

2018

Sensors

View full text Add to dashboard Cite

Applying people detectors to unseen data is challenging since patterns distributions, such as viewpoints, motion, poses, backgrounds, occlusions and people sizes, may significantly differ from the ones of the training dataset. In this paper, we propose a coarse-to-fine framework to adapt frame by frame people detectors during runtime classification, without requiring any additional manually labeled ground truth apart from the offline training of the detection model. Such adaptation make use of multiple detectors mutual information, i.e., similarities and dissimilarities of detectors estimated and agreed by pair-wise correlating their outputs. Globally, the proposed adaptation discriminates between relevant instants in a video sequence, i.e., identifies the representative frames for an adaptation of the system. Locally, the proposed adaptation identifies the best configuration (i.e., detection threshold) of each detector under analysis, maximizing the mutual information to obtain the detection threshold of each detector. The proposed coarse-to-fine approach does not require training the detectors for each new scenario and uses standard people detector outputs, i.e., bounding boxes. The experimental results demonstrate that the proposed approach outperforms state-of-the-art detectors whose optimal threshold configurations are previously determined and fixed from offline training data.

show abstract

Adapting pedestrian detectors to new domains: A comprehensive review

Cited by 12 publications

References 62 publications

Real‐time face recognition based on pre‐identification and multi‐scale classification

Real‐time face recognition based on pre‐identification and multi‐scale classification

Coupling digital simulation and machine learning metamodel through an active learning approach in Industry 4.0 context

Coarse-to-Fine Adaptive People Detection for Video Sequences by Maximizing Mutual Information †

Contact Info

Product

Resources

About