We aim to sense/monitor public space using emerging data and cutting-edge technologies using images from CCTV or (hunting) cameras we set by ourselves, Wi-Fi probes, wearable cameras and deep learning algorithms. We aim to digitalize Jan Gehl's theory in this project.
Small public spaces are the key built environment elements that provide venues for various of activities. However, existing measurements or approaches could not efficiently and effec- tively quantify how small public spaces are being used. In this paper, we utilized a deep con- volutional neural network to quantify the usage of small public spaces through recorded videos as a reliable and robust method to bridge the literature gap. To start with, we deployed photographic devices to record videos that cover the minimum enclosing square of a small public space for a certain period of time, then utilized a deep convolutional neural network to detect people in these videos and converted their location from image-based position to real-world projected coordinates. To validate the accuracy and robustness of the method, we experimented our approach in a residential community in Beijing, and our results confirmed that the usage of small public spaces could be measured and quantified effectively and efficiently.
People and their activities are the core of the vitality of urban public space. The measurement of public space vitality focusing on people and their activities has always been a difficulty in human-scale urban researches. In view of the representation of public space vitality, this research proposes a new method of spatial vitality representation based on the crowd trajectory clustering. In this method, the multi-object tracking technology based on videos is used to extract the trajectory of the crowd, which is further clustered based on the trajectory structure. According to the diversity of trajectory categories and the difference of structures, “the space trajectory entropy” is put forward to reflect the diversity and mixing degree of the behavior patterns in public space, and to measure the complex state of crowd activity from a novel and concise perspective, so as to represent the vitality of public space. In this research, three public spaces in Wuhou District of Chengdu City are selected as the research objects. The spatial trajectory entropy of the three scenes is calculated under this method. Combined with manual review, it explores the changes and causes of the time series of spatial vitality of the three scenes and gives spatial optimization suggestions. The results show that the spatial vitality characterization method can objectively describe the temporal and spatial movement of the crowd, precisely reflect the spatial-temporal vitality of space, reflect the exact urban operation and maintenance reality in the space, and contribute to establish a human-scale dynamic evaluation mechanism of spatial vitality. As a result, the proposed work can provide precise technical support for city governance, such as public space vitality assessment, quality optimization and site micro-renewal.