Efficient Single Object Detection on Image Patches with Early Exit Enhanced High-Precision CNNs

TL;DR

This paper introduces an efficient CNN architecture with early exit strategies for high-precision object detection on resource-limited robotic platforms, achieving high accuracy and significant runtime optimization.

Contribution

It presents a novel CNN with integrated Early Exits tailored for real-time object detection in robotics, reducing computational cost while maintaining high accuracy.

Findings

100% precision on validation dataset

87% recall rate

28% average runtime reduction

Abstract

This paper proposes a novel approach for detecting objects using mobile robots in the context of the RoboCup Standard Platform League, with a primary focus on detecting the ball. The challenge lies in detecting a dynamic object in varying lighting conditions and blurred images caused by fast movements. To address this challenge, the paper presents a convolutional neural network architecture designed specifically for computationally constrained robotic platforms. The proposed CNN is trained to achieve high precision classification of single objects in image patches and to determine their precise spatial positions. The paper further integrates Early Exits into the existing high-precision CNN architecture to reduce the computational cost of easily rejectable cases in the background class. The training process involves a composite loss function based on confidence and positional losses with dynamic weighting and data augmentation. The proposed approach achieves a precision of 100% on the validation dataset and a recall of almost 87%, while maintaining an execution time of around 170 $\mu$s per hypotheses. By combining the proposed approach with an Early Exit, a runtime optimization of more than 28%, on average, can be achieved compared to the original CNN. Overall, this paper provides an efficient solution for an enhanced detection of objects, especially the ball, in computationally constrained robotic platforms.