Building Robust Industrial Applicable Object Detection Models Using Transfer Learning and Single Pass Deep Learning Architectures

Abstract

The uprising trend of deep learning in computer vision and artificial intelligence can simply not be ignored. On the most diverse tasks, from recognition and detection to segmentation, deep learning is able to obtain state-of-the-art results, reaching top notch performance. In this paper we explore how deep convolutional neural networks dedicated to the task of object detection can improve our industrial-oriented object pipelines, using state-of-the-art open source deep learning frameworks, like Darknet. By using a deep learning architecture that integrates region proposals, classification and probability estimation in a single run, we aim at obtaining real-time performance. We focus on reducing the needed amount of training data drastically by exploring transfer learning, while still maintaining a high average precision. Furthermore we apply these algorithms to several applications. We start with a dummy case of rock-scissors-paper to prove the concept, followed by two industrial relevant applications, one being the detection of promotion boards in eye tracking data and the other detecting and recognizing packages of warehouse products for augmented advertisements. These applications prove the efficiency of the deep object detection algorithm in both single- and multi-class scenarios.