On Detection of Multiple Object Instances Using Hough Transforms

Barinova, Olga; Lempitsky, Victor; Kholi, P.

doi:10.1109/tpami.2012.79

Cited by 200 publications

(129 citation statements)

References 24 publications

Supporting

Mentioning

127

Contrasting

Unclassified

Order By: Relevance

“…For evaluation on the Crossing scene, we used the annotations from [68], providing a total number of 1,216 bounding boxes. This annotation is even more detailed than the one presented in [69] with 1,018 bounding boxes. For our experiments, we rescaled the images by a factor of 0:5 and doubled the training image set by including also the horizontally flipped images.…”

Section: Person Detection On Tu Darmstadt Databasesmentioning

confidence: 99%

“…Please note that the results of [68] are based on a different baseline implementation. Additionally, we include the results obtained with the publicly available code for the approach of [69]. Finally, we also list the scores obtained in our recent work [46] being trained according to the same training protocol and parameters as for our structured class-label Hough forest.…”

Section: Person Detection On Tu Darmstadt Databasesmentioning

confidence: 99%

“…This database consists of 71 images showing walking pedestrians at severe scale differences and partial occlusions. The ground truth we use has been released with [69] and contains a total number of 314 pedestrians. Fig.…”

Section: Evaluation On Campus Scenementioning

confidence: 99%

See 2 more Smart Citations

Structured Labels in Random Forests for Semantic Labelling and Object Detection

Kontschieder

Bulò

Pelillo

et al. 2014

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Ensembles of randomized decision trees, known as Random Forests, have become a valuable machine learning tool for addressing many computer vision problems. Despite their popularity, few works have tried to exploit contextual and structural information in random forests in order to improve their performance. In this paper, we propose a simple and effective way to integrate contextual information in random forests, which is typically reflected in the structured output space of complex problems like semantic image labelling. Our paper has several contributions: We show how random forests can be augmented with structured label information and be used to deliver structured low-level predictions. The learning task is carried out by employing a novel split function evaluation criterion that exploits the joint distribution observed in the structured label space. This allows the forest to learn typical label transitions between object classes and avoid locally implausible label configurations. We provide two approaches for integrating the structured output predictions obtained at a local level from the forest into a concise, global, semantic labelling. We integrate our new ideas also in the Hough-forest framework with the view of exploiting contextual information at the classification level to improve the performance on the task of object detection. Finally, we provide experimental evidence for the effectiveness of our approach on different tasks: Semantic image labelling on the challenging MSRCv2 and CamVid databases, reconstruction of occluded handwritten Chinese characters on the Kaist database and pedestrian detection on the TU Darmstadt databases.

show abstract

Section: Person Detection On Tu Darmstadt Databasesmentioning

confidence: 99%

Section: Person Detection On Tu Darmstadt Databasesmentioning

confidence: 99%

See 1 more Smart Citation

Structured Labels in Random Forests for Semantic Labelling and Object Detection

Kontschieder

Bulò

Pelillo

et al. 2014

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…The comparison results of the proposed system and four other state-of-the-art detectors (CAB [9], SVM [7], GAB [25], and HF algorithm [8]) are shown in Table 1. In order to demonstrate the superiority of the proposed system, two sets of detection rates and the corresponding average number of false positives per frame of the proposed system are shown in the first two columns of Table 1.…”

Section: Methodsmentioning

confidence: 99%

A High Accuracy Pedestrian Detection System Combining a Cascade AdaBoost Detector and Random Vector Functional-Link Net

Wang

Yoon

Xie

et al. 2014

The Scientific World Journal

View full text Add to dashboard Cite

In pedestrian detection methods, their high accuracy detection rates are always obtained at the cost of a large amount of false pedestrians. In order to overcome this problem, the authors propose an accurate pedestrian detection system based on two machine learning methods: cascade AdaBoost detector and random vector functional-link net. During the offline training phase, the parameters of a cascade AdaBoost detector and random vector functional-link net are trained by standard dataset. These candidates, extracted by the strategy of a multiscale sliding window, are normalized to be standard scale and verified by the cascade AdaBoost detector and random vector functional-link net on the online phase. Only those candidates with high confidence can pass the validation. The proposed system is more accurate than other single machine learning algorithms with fewer false pedestrians, which has been confirmed in simulation experiment on four datasets.

show abstract

“…The V(y j ) values represent the confidence measures for each hypothesis vote. In a Hough image, mean-shift is used to find the maxima in an alternative way as Hough voting-based frameworks [1,16]. If votes for the head pose θ are θ yj (θ L | c, θ L-1 ) in the patch location y j , then we set the weighted Hough voting model as…”

Section: Weighted and Cascaded Hough Votingmentioning

confidence: 99%

Dirichlet-tree cascaded Hough forests for continuous head pose estimation

Liu

Chen

2014

2014 7th International Congress on Image and Signal Processing

View full text Add to dashboard Cite

We propose a hierarchical regression approach, Dirichlet-tree cascaded Hough forests (DCHF), which is based on deep learning for continuous head pose estimation in unconstrained environment, e.g., poses, illumination, occlusion, low image resolution, expressions and make-up. First, positive facial patches are learned and extracted from facial area to eliminate the influence of noise. Then, in order to estimate continuous head pose efficiently, multiple probability models are learned in four layers of the DCHF, i.e., the patch's classification, the head pose angles, and offset probabilities mapping in the Hough space in a hierarchical way. Moreover, our algorithm takes a weighted and cascaded Hough voting method, where each positive patch extracted from the face can cast the efficient vote for head pose estimation. Experimental results on different public databases demonstrate the robustness and accuracy of the proposed approach to continuous head pose estimation. Keywords-component; continuous head pose estimation; DCHF; deep and hierarchical learning; weighted and cascaded Hough voting I.

show abstract

On Detection of Multiple Object Instances Using Hough Transforms

Cited by 200 publications

References 24 publications

Structured Labels in Random Forests for Semantic Labelling and Object Detection

Structured Labels in Random Forests for Semantic Labelling and Object Detection

A High Accuracy Pedestrian Detection System Combining a Cascade AdaBoost Detector and Random Vector Functional-Link Net

Dirichlet-tree cascaded Hough forests for continuous head pose estimation

Contact Info

Product

Resources

About