A desicion-theoretic generalization of on-line learning and an application to boosting

Freund, Yoav; Schapire, Robert E.

doi:10.1007/3-540-59119-2_166

Cited by 2,194 publications

(932 citation statements)

References 8 publications

Supporting

Mentioning

904

Contrasting

Unclassified

Order By: Relevance

“…AdaBoost is a machine learning method that combines multiple weak classifiers, each of which only returns a true or false, so that an effective strong classifier is constructed [3].…”

Section: Adaboost Classifiersmentioning

confidence: 99%

“…The image-based human detection generally consists of two stages; calculation of feature amount of given images and pattern classification based on machine learning. In this implementation, histograms of oriented gradients (HOG) [2] and AdaBoost classifiers [3] are used as feature amount and pattern classifiers, respectively. The HOG feature roughly describes object shape of local regions of given images and this is widely used for various object recognition such as pedestrian and car detection [4]- [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

FPGA Implementation of Human Detection by HOG Features with AdaBoost

Dohi

Negi

Shibata

et al. 2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe implement external memory-free deep pipelined FPGA implementation including HOG feature extraction and AdaBoost classification. To construct our design by compact FPGA, we introduce some simplifications of the algorithm and aggressive use of stream oriented architectures. We present comparison results between our simplified fixed-point scheme and an original floating-point scheme in terms of quality of results, and the results suggest the negative impact of the simplified scheme for hardware implementation is limited. We empirically show that, our system is able to detect human from 640 × 480 VGA images at up to 112 FPS on a Xilinx Virtex-5 XC5VLX50 FPGA.

show abstract

“…AdaBoost is a machine learning method that combines multiple weak classifiers, each of which only returns a true or false, so that an effective strong classifier is constructed [3].…”

Section: Adaboost Classifiersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

FPGA Implementation of Human Detection by HOG Features with AdaBoost

Dohi

Negi

Shibata

et al. 2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…The AdaBoost algorithm was first introduced in (Freund & Schapire, 1997). The purpose of this algorithm is to combine several weak classifiers into a strong classifier.…”

Section: Feature Selection and Classifier Trainingmentioning

confidence: 99%

Self‐supervised learning to visually detect terrain surfaces for autonomous robots operating in forested terrain

Zhou

McDaniel

et al. 2012

Journal of Field Robotics

View full text Add to dashboard Cite

Autonomous robotic navigation in forested environments is difficult because of the highly variable appearance and geometric properties of the terrain. In most navigation systems, researchers assume a priori knowledge of the terrain appearance properties, geometric properties, or both. In forest environments, vegetation such as trees, shrubs, and bushes has appearance and geometric properties that vary with change of seasons, vegetation age, and vegetation species. In addition, in forested environments the terrain surface is often rough, sloped, and/or covered with a surface layer of grass, vegetation, or snow. The complexity of the forest environment presents difficult challenges for autonomous navigation systems. In this paper, a self-supervised sensing approach is introduced that attempts to robustly identify a drivable terrain surface for robots operating in forested terrain. The sensing system employs both LIDAR and vision sensor data. There are three main stages in the system: feature learning, feature training, and terrain prediction. In the feature learning stage, 3D range points from LIDAR are analyzed to obtain an estimate of the ground surface location. In the feature training stage, the ground surface estimate is used to train a visual classifier to discriminate between ground and nonground regions of the image. In the prediction stage, the ground surface location can be estimated at high frequency solely from vision sensor data. C 2012 Wiley Periodicals, Inc.

show abstract

“…• The development of many powerful, mainly discriminative methodologies such as Boosting [31], Support Vector machines [32] and their recent structural extension [33] and (deep) neural network architectures [34] which can harness the amount of information provided by the above mentioned modern large scale datasets and facilitate training of complex deformable object and facial models [35].…”

Section: Introductionmentioning

confidence: 99%