Machine Learning at Scale: How Big Data and AI are Transforming Engineering

96.6K
views
29
authors
6
articles
Cover image for research topic "Machine Learning at Scale: How Big Data and AI are Transforming Engineering"
Editors
2
Impact
Loading...
Original Research
05 October 2018

Convolutional neural networks (CNN) have enabled significant improvements in pedestrian detection owing to the strong representation ability of the CNN features. However, it is generally difficult to reduce false positives on hard negative samples such as tree leaves, traffic lights, poles, etc. Some of these hard negatives can be removed by making use of high level semantic vision cues. In this paper, we propose a region-based CNN method which makes use of semantic cues for better pedestrian detection. Our method extends the Faster R-CNN detection framework by adding a branch of network for semantic image segmentation. The semantic network aims to compute complementary higher level semantic features to be integrated with the convolutional features. We make use of multi-resolution feature maps extracted from different network layers in order to ensure good detection accuracy for pedestrians at different scales. Boosted forest is used for training the integrated features in a cascaded manner for hard negatives mining. Experiments on the Caltech pedestrian dataset show improvements on detection accuracy with the semantic network. With the deep VGG16 model, our pedestrian detection method achieves robust detection performance on the Caltech dataset.

20,720 views
46 citations
31,123 views
16 citations
Open for submission
Frontiers Logo

Frontiers in Robotics and AI

Computer Intelligence for Energy-Efficient Robotic Systems
Edited by Eileen L.M. Su, William Holderbaum, Ziwei Wang
Deadline
04 July 2025
Submit a paper
Recommended Research Topics
Frontiers Logo

Frontiers in Robotics and AI

Cognitive Robotics - Cognitive computations for robotics, agent and HSI applications
Edited by Zdzislaw KOWALCZUK
44.8K
views
13
authors
5
articles
Frontiers Logo

Frontiers in Robotics and AI

Robots that Learn and Reason: Towards Learning Logic Rules from Noisy Data
Edited by Kristian Kersting, Plinio Moreno, José Santos-Victor, Alexandre Bernardino, Rodrigo Ventura
26.3K
views
27
authors
5
articles
Frontiers Logo

Frontiers in Robotics and AI

Artificial Intelligence Solutions For Decision Making In Robotics
Edited by Qasem Abu Al-Haija, Wejdan Abu Elhaija, Moez Krichen
23K
views
13
authors
5
articles
Frontiers Logo

Frontiers in Robotics and AI

Artificial Intelligence and Robotic Applications for Smart Monitoring and Assistance in Healthcare Services
Edited by Massimo Esposito, Umberto Maniscalco, Giovanni Luca Christian Masala
14.4K
views
32
authors
6
articles
Frontiers Logo

Frontiers in Robotics and AI

Language, Affordance and Physics in Robot Cognition and Intelligent Systems
Edited by Nutan Chen, Walterio W Mayol-Cuevas, Herke Van Hoof, Aurelio Cortese, Maximilian Karl, Andy Zeng, Wolfram Burgard
32.5K
views
21
authors
7
articles