In this paper, we introduce a new technique that combines two popular methods to estimate uncertainty in object detection. Quantifying uncertainty is critical in real-world robotic applications. Traditional detection models can be ambiguous even when they provide a high-probability output. Robot actions based on high-confidence, yet unreliable predictions, may result in serious repercussions. Our framework employs deep ensembles and Monte Carlo dropout for approximating predictive uncertainty, and it improves upon the uncertainty estimation quality of the baseline method. The proposed approach is evaluated on publicly available synthetic image datasets captured from sequences of video.

翻译：在本文中,我们引入了一种新技术,结合两种流行的方法来估计物体探测的不确定性。量化不确定性对于现实世界的机器人应用至关重要。传统的检测模型即使提供高概率输出,也可能含糊不清。基于高度自信的机器人行动,但不可靠的预测,可能会造成严重的后果。我们的框架使用深层组合和蒙特卡洛辍学来估计预测不确定性,并改进基线方法的不确定性估计质量。拟议方法根据从视频序列中采集的公开的合成图像数据集进行评估。