A
Aharon Bar Hillel
Researcher at Ben-Gurion University of the Negev
Publications - 7
Citations - 813
Aharon Bar Hillel is an academic researcher from Ben-Gurion University of the Negev. The author has contributed to research in topics: Object detection & Random subspace method. The author has an hindex of 4, co-authored 7 publications receiving 682 citations. Previous affiliations of Aharon Bar Hillel include General Motors.
Papers
More filters
Journal ArticleDOI
Recent progress in road and lane detection: a survey
TL;DR: This paper presents a generic break down of the problem of road or lane perception into its functional building blocks and elaborate the wide range of proposed methods within this scheme.
Journal ArticleDOI
Detection and counting of flowers on apple trees for better chemical thinning decisions
TL;DR: An algorithm is developed and trained with three stages: a visual flower detector based on a deep convolutional neural network, followed by a blooming level estimator, and a peak blooming day finding algorithm that identified correctly the orchard’s blooming peak date, which was used to determine the thinning date in the current practice.
Patent
Vision-based object detection by part-based feature synthesis
Dan Levi,Aharon Bar Hillel +1 more
TL;DR: In this paper, a method for training and using an object classifier to identify a class object from a captured image is provided for training, where a plurality of still images are obtained from training data and a feature generation technique is applied to the plurality for identifying candidate features from each respective image.
Patent
Complex-object detection using a cascade of classifiers
Dan Levi,Aharon Bar Hillel +1 more
TL;DR: In this paper, a cascade of classifiers are used to identify complex-objects parts in an image in which successive classifiers process pixel patches on condition that respective discriminatory features sets of previous classifiers have been identified and selecting additional pixel patches from a query image by applying known positional relationships between an identified complex-object part and another part to be identified.
Journal ArticleDOI
Information Constrained Control Analysis of Eye Gaze Distribution Under Workload
TL;DR: It is shown that the model can be used to visualize the unknown reward function associated with a task, and predict human workload based on gaze pattern, and confirm the theoretical predictions with respect to the low rank manifold and order relations in the data.