International Conference on Research for Transport and Logistics Industry

Permanent URI for this communityhttp://192.248.9.226/handle/123/17481

Browse

Browsing International Conference on Research for Transport and Logistics Industry by Author "Aithal, BH"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    item: Conference-Full-text
    Deep learning-based automatic building types classification for transport planning
    (Sri Lanka Society of Transport and Logistics, 2023-08-26) Khatua, A; Goswami, AK; Aithal, BH; Gunaruwan, TL
    The present study proposes a building classification algorithm that uses deep learning techniques, namely object detection and image segmentation, to distinguish between residential and commercial structures. The algorithm is trained using images from the ISPRS Potsdam and Spacenet 3 (Vegas) datasets. According to the model's results, the model has obtained high precision, recall, and mean average precision (mAP) values for both classes. Despite the high-performance yield of the model, the robustness the model can be improved by expanding the training dataset to include more building images from diverse locations on Earth.
  • Thumbnail Image
    item: Conference-Full-text
    Land-use change dynamics and automated feature extraction using high-resolution satellite imagery
    (Sri Lanka Society of Transport and Logistics, 2022-08) Dey, M; Prakash, PS; Chandrashekar, CM; Aithal, BH; Perera, N; Thibbotuwawa, A
    The mapping of urban landscapes is a challenging task due to their dense and diverse characteristics. The changing urban environment with developing infrastructure demands constant updates and accurate extraction techniques. Recent advancement in geospatial technology has led to the capture of high-resolution data and its analysis at a finer scale. However, a sustainable development framework necessitates the understanding of spatial patterns incorporating vertical and horizontal components of the built-up volume. This study aims to understand the changing landscape at the pixel level by analysing features along with their volumetric expansion. The findings highlight that Bangalore city’s urban growth has shown increment over the period with volumetric expansion in all parts of the city based on events of changing demand and growth. The evaluation metrics indicate that the model can be generalised for any geographical location as well as to different sensor type images.