自行车运动员意图检测的概率方法
Cyclist Intention Detection: A Probabilistic Approach
摘要：
本文提出了一种整体的方法，概率骑自行车的意图检测。使用基于运动历史图像（MHI）的基本运动检测和残差卷积神经网络（ResNet）来估计当前循环运动状态的概率。这些概率被用作概率集合轨迹预测中的权重。集合由专门的模型组成，这些模型在骑自行车者的某种运动状态（例如骑自行车者正在开始或左转）的假设下以高斯分布的形式产生个体预测。通过对专用模型进行加权，我们以高斯混合的形式创建预测，该混合定义了骑自行车者将以一定概率居住的区域。为了评估我们的方法，我们对预测分布的可靠性、清晰度和位置准确性进行了评级。我们将我们的方法与以高斯分布形式产生预测的单一模型方法进行比较，并表明我们的方法能够产生更可靠，更清晰的输出，同时保持可比的位置精度。这两种方法都使用在公共交通路口创建的数据集进行评估。我们的代码和数据集是公开的。
英文摘要：
This article presents a holistic approach for probabilistic cyclist intention detection. A basic movement detection based on motion history images (MHI) and a residual convolutional neural network (ResNet) are used to estimate probabilities for the current cyclist motion state. These probabilities are used as weights in a probabilistic ensemble trajectory forecast. The ensemble consists of specialized models, which produce individual forecasts in the form of Gaussian distributions under the assumption of a certain motion state of the cyclist (e.g. cyclist is starting or turning left). By weighting the specialized models, we create forecasts in the from of Gaussian mixtures that define regions within which the cyclists will reside with a certain probability. To evaluate our method, we rate the reliability, sharpness, and positional accuracy of our forecasted distributions. We compare our method to a single model approach which produces forecasts in the form of Gaussian distributions and show that our method is able to produce more reliable and sharper outputs while retaining comparable positional accuracy. Both methods are evaluated using a dataset created at a public traffic intersection. Our code and the dataset are made publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
