Stride length estimation is one of the most crucial aspects of Pedestrian Dead Reckoning (PDR). Due to the measurement noise of inertial sensors, individual variances of pedestrians, and the uncertainty in pedestrians walking, there is a substantial error in the assessment of stride length, which causes the accumulated deviation of Pedestrian Dead Reckoning (PDR). With the help of multi-gait analysis, which decomposes strides in time and space with greater detail and accuracy, a novel and revolutionary stride estimating model or scheme could improve the performance of PDR on different users. This paper presents a diverse stride gait dataset by using inertial sensors that collect foot movement data from people of different genders, heights, and walking speeds. The dataset contains 4690 walking strides data and 19,083 gait labels. Based on the dataset, we propose a threshold-independent stride segmentation algorithm called SDATW and achieve an F-measure of 0.835. We also provide the detailed results of recognizing four gaits under different walking speeds, demonstrating the utility of our dataset for helping train stride segmentation algorithms and gait detection algorithms.

The Non-local self-attention mechanism can significantly improve the capability of feature representation with long-range dependencies at the cost of high computational complexity. To address the issue, the self-attention-based autoregressive axial transformer has been proposed to apply attention along a single axis of the feature maps instead of the whole ones with large receptive fields. It performs axial-attention twice along the height- and width-axis respectively in the spatial dimension of the feature maps for the image data. However, there is still room for improvement. We can convert the 2D spatial feature map into a 1D feature sequence and just perform axial-attention once along it to save more computing resources. Motivated by the insight, we propose an Efficient Axial-Attention Network (EAAN) for video-based person re-identification (Re-ID) to reduce computation and improve accuracy by serializing feature maps with multi-granularity and reducing the number of axial-attention runs. We also introduce a deserialization approach that can restore the shape of the feature maps. Moreover, we expand the CTN (Channel Transformer Network) to a wider range of uses. Additionally, we verify that the serialized feature sequence can enhance expressiveness in our EAAN with lower complexity. Experiments on MARS and DukeMTMC-VideoReID (DukeV) datasets show outstanding performance in computation efficiency and accuracy. It not only outperforms the state-of-the-art method on MARS by 0.3% in both Rank-1 and mAP, and surpasses that on DukeV by 0.1% in Rank-1 with equal mAP, but also reduces parameters and GFLOPS (Giga Floating-point Operations Per Second) by 16.9% and 6.6% respectively compared to another axial-attention-based method. The code will be available at https://github.com/hopstone/EAAN.

Accurate and reliable stride length estimation modules play a significant role in Pedestrian Dead Reckoning (PDR) systems, but the accuracy of stride length calculation suffers from individual differences. This paper presents a stride length prediction strategy for PDR systems that can be adapted across individuals and broad walking velocity fields. It consists of a multi-gait division algorithm, which can divide a full stride into push-off, swing, heel-strike, and stance based on multi-axis IMU data. Additionally, based on the acquired gait phases, the correlation between multiple features of distinct gait phases and the stride length is analyzed, and multi regression models are merged to output the stride length value. In experimental tests, the gait segmentation algorithm provided gait phases division with the F-score of 0.811, 0.748, 0.805, and 0.819 for stance, push-off, swing, heel-strike, respectively, and IoU of 0.482, 0.69, 0.509 for push-off, swing, heel-strike, respectively. The root means square error (RMSE) of our proposed stride length estimation was 151.933, and the relative error for total distance in varying walking speed tests was less than 2%. The experimental results validated that our proposed gait phase segmentation algorithm can accurately recognize gait phases for individuals with wide walking speed ranges. With no need for parameter modification, the stride length method based on the fusion of multiple predictions from different gait phases can provide better accuracy than the estimations based on the full stride.