Vehicles Tracking by Combining Convolutional Neural Network Based Segmentation and Optical Flow Estimation
| Autor: | Sébastien Ambellouis, Jacques Boonaert, Abdelmalik Taleb Ahmed, Tuan-Hung Vu |
|---|---|
| Přispěvatelé: | Ecole nationale supérieure Mines-Télécom Lille Douai (IMT Lille Douai), Institut Mines-Télécom [Paris] (IMT), Laboratoire Électronique Ondes et Signaux pour les Transports (COSYS-LEOST ), Université de Lille-Université Gustave Eiffel, Laboratoire d'Automatique, de Mécanique et d'Informatique industrielles et Humaines - UMR 8201 (LAMIH), Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-INSA Institut National des Sciences Appliquées Hauts-de-France (INSA Hauts-De-France), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA) |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
RESEAU NEURONAL
DETECTION D&apos VEHICULE Computer science OPTIQUE Optical flow SEGMENTATION 02 engineering and technology Tracking (particle physics) Convolutional neural network OPTICAL FLOW CAPTEUR OPTIQUE Bounding overwatch INSTANCE SEGMENTATION 0202 electrical engineering electronic engineering information engineering Computer vision Segmentation TRAITEMENT DES IMAGES business.industry Detector Process (computing) VEHICLES TRACKING Video tracking 020201 artificial intelligence & image processing Artificial intelligence OBJET business [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing |
| Zdroj: | ACIVS 2020, 20th International Conference on Advanced Concepts for Intelligent Vision Systems ACIVS 2020, 20th International Conference on Advanced Concepts for Intelligent Vision Systems, Feb 2020, Auckland, New Zealand. pp529-540, ⟨10.1007/978-3-030-40605-9_45⟩ ACIVS 2020, 20th International Conference on Advanced Concepts for Intelligent Vision Systems, Feb 2020, Auckland, France. pp529-540, ⟨10.1007/978-3-030-40605-9_45⟩ Advanced Concepts for Intelligent Vision Systems ISBN: 9783030406042 ACIVS |
| DOI: | 10.1007/978-3-030-40605-9_45⟩ |
| Popis: | ACIVS 2020, 20th International Conference on Advanced Concepts for Intelligent Vision Systems, Auckland, NOUVELLE-ZELANDE, 10-/02/2020 - 14/02/2020; Object tracking is an important proxy task towards action recognition. The recent successful CNN models for detection and segmentation, such as Faster R-CNN and Mask R-CNN lead to an effective approach for tracking problem: tracking-by-detection. This very fast type of tracker takes into account only the Intersection-Over-Union (IOU) between bounding boxes to match objects without any other visual information. In contrast, the lack of visual information of IOU tracker combined with the failure detections of CNNs detectors create fragmented trajectories. Inspired by the work of Luc et al that predicts future segmentations by using Optical flow, we propose an enhanced tracker based on tracking-by-detection and optical flow estimation in vehicle tracking scenario. Our solution generates new detections or segmentations based on translating backward and forward results of CNNs detectors by optical flow vectors. This task can fill in the gaps of trajectories. The qualitative results show that our solution achieved stable performance with different types of flow estimation methods. Then we match generated results with fragmented trajectories by SURF features. DAVIS dataset is used for evaluating the best way to generate new detections. Finally, the entire process is test on DETRAC dataset. The qualitative results show that our methods significantly improve the fragmented trajectories. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|