Improving multi-class Boosting-based object detection

Article type: Research Article

Authors: Buenaposada, José Miguel^{a; *} | Baumela, Luis^b

Affiliations: [a] ETSII, Universidad Rey Juan Carlos, Móstoles, Spain | [b] Departamento de Inteligencia Artificial, Universidad Politécnica de Madrid, Spain

Correspondence: [*] Corresponding author: José Miguel Buenaposada, ETSII, Universidad Rey Juan Carlos, Móstoles, Spain. E-mail: josemiguel.buenaposada@urjc.es.

Abstract: In recent years we have witnessed significant progress in the performance of object detection in images. This advance stems from the use of rich discriminative features produced by deep models and the adoption of new training techniques. Although these techniques have been extensively used in the mainstream deep learning-based models, it is still an open issue to analyze their impact in alternative, and computationally more efficient, ensemble-based approaches. In this paper we evaluate the impact of the adoption of data augmentation, bounding box refinement and multi-scale processing in the context of multi-class Boosting-based object detection. In our experiments we show that use of these training advancements significantly improves the object detection performance.

Keywords: Object detection, multi-class Boosting, data augmentation, bounding box adjust

DOI: 10.3233/ICA-200636

Journal: Integrated Computer-Aided Engineering, vol. 28, no. 1, pp. 81-96, 2021