%0 Conference Paper %1 7225690 %A Fukui, H. %A Yamashita, T. %A Yamauchi, Y. %A Fujiyoshi, H. %A Murase, H. %B 2015 IEEE Intelligent Vehicles Symposium (IV) %D 2015 %K dnn lidar order1 pedestrian %P 223-228 %R 10.1109/IVS.2015.7225690 %T Pedestrian detection based on deep convolutional neural network with ensemble inference network %U https://ieeexplore.ieee.org/document/7225690 %X Pedestrian detection is an active research topic for driving assistance systems. To install pedestrian detection in a regular vehicle, however, there is a need to reduce its cost and ensure high accuracy. Although many approaches have been developed, vision-based methods of pedestrian detection are best suited to these requirements. In this paper, we propose the methods based on Convolutional Neural Networks (CNN) that achieves high accuracy in various fields. To achieve such generalization, our CNN-based method introduces Random Dropout and Ensemble Inference Network (EIN) to the training and classification processes, respectively. Random Dropout selects units that have a flexible rate, instead of the fixed rate in conventional Dropout. EIN constructs multiple networks that have different structures in fully connected layers. The proposed methods achieves comparable performance to state-of-the-art methods, even though the structure of the proposed methods are considerably simpler.

@inproceedings{7225690, abstract = {Pedestrian detection is an active research topic for driving assistance systems. To install pedestrian detection in a regular vehicle, however, there is a need to reduce its cost and ensure high accuracy. Although many approaches have been developed, vision-based methods of pedestrian detection are best suited to these requirements. In this paper, we propose the methods based on Convolutional Neural Networks (CNN) that achieves high accuracy in various fields. To achieve such generalization, our CNN-based method introduces Random Dropout and Ensemble Inference Network (EIN) to the training and classification processes, respectively. Random Dropout selects units that have a flexible rate, instead of the fixed rate in conventional Dropout. EIN constructs multiple networks that have different structures in fully connected layers. The proposed methods achieves comparable performance to state-of-the-art methods, even though the structure of the proposed methods are considerably simpler.}, added-at = {2020-05-27T23:01:12.000+0200}, author = {{Fukui}, H. and {Yamashita}, T. and {Yamauchi}, Y. and {Fujiyoshi}, H. and {Murase}, H.}, biburl = {https://www.bibsonomy.org/bibtex/296a8a1dae36aeda9c35cf8eddb079aa1/sohnki}, booktitle = {2015 IEEE Intelligent Vehicles Symposium (IV)}, description = {Pedestrian detection based on deep convolutional neural network with ensemble inference network - IEEE Conference Publication}, doi = {10.1109/IVS.2015.7225690}, interhash = {94eb4da8e2e30fef866618dcf0e3fce9}, intrahash = {96a8a1dae36aeda9c35cf8eddb079aa1}, issn = {1931-0587}, keywords = {dnn lidar order1 pedestrian}, month = {June}, pages = {223-228}, timestamp = {2020-06-02T20:02:27.000+0200}, title = {Pedestrian detection based on deep convolutional neural network with ensemble inference network}, url = {https://ieeexplore.ieee.org/document/7225690}, year = 2015 }