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.
翻译:本文介绍了一种全方位的概率周期性测测方法。 依据运动历史图像( MHI) 和残留神经神经网络( ResNet) 进行基本运动检测, 以估计当前自行车运动状态的概率。 这些概率在概率共和轨预测中用作加权值。 组合由专门模型组成, 这些模型根据骑自行车者某种运动状态( 例如骑自行车者正在开始或转向左转) 的假设, 以高斯分布方式产生个别预测。 通过加权专门模型, 我们从高斯混合物中生成预测, 确定骑自行车者所居住的区域, 具有一定的概率。 为了评估我们的方法, 我们用预测分布的可靠性、 锐度和定位准确性来评估我们预测的分布的可靠性。 我们比较了我们的方法, 将我们的方法与一种单一模型方法进行比较, 该模型以高斯分布方式进行预测, 并显示我们的方法能够产生更可靠和更精确的产出, 同时保持可比较的定位准确性。 两种方法都是用一种可比较的数据来评估的。 两种方法都是用一种可公开的数据设置的交叉。