Semantic segmentation is one of the computer vision tasks which is widely researched at present. It plays an essential role to adapt and apply for real-world use-cases, including the application with autonomous driving systems. To further study self-driving cars in Thailand, we provide both the proposed methods and the proposed dataset in this paper. In the proposed method, we contribute Deeplab-V3-A1 with Xception, which is an extension of DeepLab-V3+ architecture. Our proposed method as DeepLab-V3-A1 with Xception is enhanced by the different number of $1\times1$ convolution layers on the decoder side and refining the image classification backbone with modification of the Xception model. The experiment was conducted on four datasets: the proposed dataset and three public datasets i.e., the CamVid, the cityscapes, and IDD datasets, respectively. The results show that our proposed strategy as DeepLab-V3-A1 with Xception performs comparably to the baseline methods for all corpora including measurement units such as mean IoU, F1 score, Precision, and Recall. In addition, we benchmark DeepLab-V3-A1 with Xception on the validation set of the cityscapes dataset with a mean IoU of 78.86%. For our proposed dataset, we first contribute the Bangkok Urbanscapes dataset, the urban scenes in Southeast Asia. This dataset contains the pair of input images and annotated labels for 701 images. Our dataset consists of various driving environments in Bangkok, as shown for eleven semantic classes (Road, Building, Tree, Car, Footpath, Motorcycle, Pole, Person, Trash, Crosswalk, and Misc). We hope that our architecture and our dataset would help self-driving autonomous developers improve systems for driving in many cities with unique traffic and driving conditions similar to Bangkok and elsewhere in Thailand. Our implementation codes and dataset are available at https://kaopanboonyuen.github.io/bkkurbanscapes .

The well-being of residents is a top priority for megacities, which is why urban design and sustainable development are crucial topics. Quality of Life (QoL) is used as an effective key performance index (KPI) to measure the efficiency of a city plan’s quantity and quality factors. For city dwellers, QoL for pedestrians is also significant. The walkability concept evaluates and analyzes the QoL in a walking scene. However, the traditional questionnaire survey approach is costly, time-consuming, and limited in its evaluation area. To overcome these limitations, the paper proposes using artificial intelligence (AI) technology to evaluate walkability data collected through a questionnaire survey using virtual reality (VR) tools. The proposed method involves knowledge extraction using deep convolutional neural networks (DCNNs) for information extraction and deep learning (DL) models to infer QoL scores. Knowledge distillation (KD) is also applied to reduce the model size and improve real-time performance. The experiment results demonstrate that the proposed approach is practical and can be considered an alternative method for acquiring QoL.

In the modern era, urban design and sustainable development are vital topics for megacities, as they are important for the wellbeing of its residents. One of the effective key performance indices (KPIs) measuring the city plan’s efficiency in quantity and quality factors is Quality of Life (QOL), an index that policymakers can use as a critical KPI to measure the quality of urbanscape design. In the traditional approach, the researchers conduct the questionnaire survey and then analyze the gathered data to acquire the QOL index. The conventional process is costly and time-consuming, but the result of the evaluation area is limited. Moreover, it is difficult to embed in an application or system; we proposed artificial intelligence (AI) approaches to solve the limitation of the traditional method in Bangkok as a case study. There are two steps for our proposed method. First, in the knowledge extraction step, we apply deep convolutional neural networks (DCNNs), including semantic segmentation and object detection, to extract helpful information images. Second, we use a linear regression model for inferring the QOL score. We conducted various state-of-the-art (SOTA) models and public datasets to evaluate the performance of our method. The experiment results show that our novel approach is practical and can be considered for use as an alternative QOL acquisition method. We also gain some understanding of drivers’ insights from the experiment result.