For reliable environment perception, the use of temporal information is essential in some situations. Especially for object detection, sometimes a situation can only be understood in the right perspective through temporal information. Since image-based object detectors are currently based almost exclusively on CNN architectures, an extension of their feature extraction with temporal features seems promising. Within this work we investigate different architectural components for a CNN-based temporal information extraction. We present a Temporal Feature Network which is based on the insights gained from our architectural investigations. This network is trained from scratch without any ImageNet information based pre-training as these images are not available with temporal information. The object detector based on this network is evaluated against the non-temporal counterpart as baseline and achieves competitive results in an evaluation on the KITTI object detection dataset.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Temporal Feature Networks for CNN based Object Detection


    Contributors:


    Publication date :

    2021-07-11


    Size :

    809744 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Cooperative LIDAR Object Detection via Feature Sharing in Deep Networks

    Marvasti, Ehsan Emad / Raftari, Arash / Marvasti, Amir Emad et al. | IEEE | 2020


    Intelligent Mining Road Object Detection Based on Multiscale Feature Fusion in Multi-UAV Networks

    Xinkai Xu / Shuaihe Zhao / Cheng Xu et al. | DOAJ | 2023

    Free access

    Channel Boosting Feature Ensemble for Radar-based Object Detection

    Azam, Shoaib / Munir, Farzeen / Jeon, Moongu | IEEE | 2021


    Detection of object abandonment using temporal logic

    Bhargava, M. / Chen, C. C. / Ryoo, M. S. et al. | British Library Online Contents | 2009


    Feature-Based Satellite Detection Using Convolutional Neural Networks

    Fletcher, Justin | British Library Conference Proceedings | 2019