DeepLab
In today’s world, urban design and sustainable development are crucial for megacities, impacting residents’ wellbeing. Quality of Life (QOL) is a key performance indicator (KPI) used to measure the effectiveness of city planning. Traditionally, QOL is assessed through costly and time-consuming surveys, but our AI-based approach offers a more efficient solution. Using Bangkok as a case study, we apply deep convolutional neural networks (DCNNs) for semantic segmentation and object detection to gather relevant image data. Then, we use linear regression to infer QOL scores. Our method, tested with state-of-the-art models and public datasets, proves to be a practical alternative for QOL assessment, with implementation codes and datasets available at https://kaopanboonyuen.github.io/bkkurbanscapes.
This paper addresses semantic segmentation for autonomous driving systems, focusing on self-driving cars in Thailand. We introduce DeepLab-V3-A1 with Xception, an enhanced version of DeepLab-V3+, and present the Bangkok Urbanscapes dataset. Our method improves segmentation accuracy by refining the decoder and modifying the Xception backbone. Experiments on four datasets, including CamVid, Cityscapes, IDD, and our proposed dataset, show our approach performs comparably to baseline methods. Our dataset includes 701 annotated images of various Bangkok driving environments, covering eleven semantic classes. The architecture and dataset aim to aid developers in improving autonomous driving systems for diverse urban conditions. Implementation codes and dataset are available at https://kaopanboonyuen.github.io/bkkurbanscapes.
