Artículo
Enhancing object detection for autonomous driving by optimizing anchor generation and addressing class imbalance
Autor/es | Carranza García, Manuel
Lara Benítez, Pedro García Gutiérrez, Jorge Riquelme Santos, José Cristóbal |
Departamento | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos |
Fecha de publicación | 2021 |
Fecha de depósito | 2022-02-17 |
Publicado en |
|
Resumen | Object detection has been one of the most active topics in computer vision for the past years. Recent
works have mainly focused on pushing the state-of-the-art in the general-purpose COCO benchmark.
However, the use of ... Object detection has been one of the most active topics in computer vision for the past years. Recent works have mainly focused on pushing the state-of-the-art in the general-purpose COCO benchmark. However, the use of such detection frameworks in specific applications such as autonomous driving is yet an area to be addressed. This study presents an enhanced 2D object detector based on Faster RCNN that is better suited for the context of autonomous vehicles. Two main aspects are improved: the anchor generation procedure and the performance drop in minority classes. The default uniform anchor configuration is not suitable in this scenario due to the perspective projection of the vehicle cameras. Therefore, we propose a perspective-aware methodology that divides the image into key regions via clustering and uses evolutionary algorithms to optimize the base anchors for each of them. Furthermore, we add a module that enhances the precision of the second-stage header network by including the spatial information of the candidate regions proposed in the first stage. We also explore different reweighting strategies to address the foreground-foreground class imbalance, showing that the use of a reduced version of focal loss can significantly improve the detection of difficult and underrepresented objects in two-stage detectors. Finally, we design an ensemble model to combine the strengths of the different learning strategies. Our proposal is evaluated with the Waymo Open Dataset, which is the most extensive and diverse up to date. The results demonstrate an average accuracy improvement of 6.13% mAP when using the best single model, and of 9.69% mAP with the ensemble. The proposed modifications over the Faster R-CNN do not increase computational cost and can easily be extended to optimize other anchor-based detection frameworks. |
Agencias financiadoras | Ministerio de Ciencia, Innovación y Universidades (MICINN). España Junta de Andalucía |
Identificador del proyecto | TIN2017-88209-C2
US-1263341 P18-RT-2778 |
Cita | Carranza García, M., Lara Benítez, P., García Gutiérrez, J. y Riquelme Santos, J.C. (2021). Enhancing object detection for autonomous driving by optimizing anchor generation and addressing class imbalance. Neurocomputing, 449 (August 2021), 229-244. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
Enhancing object detection for ... | 3.620Mb | [PDF] | Ver/ | |