Article: Optimisation of landscape feature intelligent recognition algorithm based on deep learning Journal: International Journal of Environment and Sustainable Development (IJESD) 2026 Vol.25 No.6 pp.87 - 107 Abstract: This paper presents a lightweight dynamic feature pyramid network (DFPN) for intelligent landscape feature recognition, tackling computational redundancy and boundary ambiguity in complex scenes. DFPN employs an adaptive scale-aware module to dynamically weight and fuse ResNet-18's multilevel features (C1-C4), while a squeeze-and-excitation (SE) channel attention mechanism amplifies critical feature responses. Deformable convolutions enable adaptive receptive fields, enhancing multi-scale landscape perception and computational efficiency. For sharper boundaries, DFPN integrates atrous spatial pyramid pooling (ASPP) with edge priors and adopts a boundary-aware dice loss to mitigate edge ambiguity. On urban, complex, and rural landscape datasets, DFPN attains 93.82% pixel accuracy and 79.1% IoU at 42.3 FPS. In cross-dataset evaluation, its mIoU drops only 12.3% on the City dataset - substantially better than U-Net's 18.7% - confirming superior generalisation. Through co-designed architecture and loss optimisation, DFPN strikes an effective balance between accuracy and efficiency, proving robust in diverse, complex landscapes. Inderscience Publishers - linking academia, business and industry through research

Title: Optimisation of landscape feature intelligent recognition algorithm based on deep learning

Authors: Weihong Wang

Addresses: School of Environmental Art and Design, Wuxi Vocational Institute of Arts & Technology, Yixing – 214206, Jiangsu, China

Abstract: This paper presents a lightweight dynamic feature pyramid network (DFPN) for intelligent landscape feature recognition, tackling computational redundancy and boundary ambiguity in complex scenes. DFPN employs an adaptive scale-aware module to dynamically weight and fuse ResNet-18's multilevel features (C1-C4), while a squeeze-and-excitation (SE) channel attention mechanism amplifies critical feature responses. Deformable convolutions enable adaptive receptive fields, enhancing multi-scale landscape perception and computational efficiency. For sharper boundaries, DFPN integrates atrous spatial pyramid pooling (ASPP) with edge priors and adopts a boundary-aware dice loss to mitigate edge ambiguity. On urban, complex, and rural landscape datasets, DFPN attains 93.82% pixel accuracy and 79.1% IoU at 42.3 FPS. In cross-dataset evaluation, its mIoU drops only 12.3% on the City dataset - substantially better than U-Net's 18.7% - confirming superior generalisation. Through co-designed architecture and loss optimisation, DFPN strikes an effective balance between accuracy and efficiency, proving robust in diverse, complex landscapes.

Keywords: deep learning; landscape feature recognition; dynamic feature pyramid network; boundary enhancement strategy; cross-dataset generalisation.

DOI: 10.1504/IJESD.2026.154274

International Journal of Environment and Sustainable Development, 2026 Vol.25 No.6, pp.87 - 107

Received: 30 Aug 2025
Accepted: 11 Mar 2026
Published online: 18 Jun 2026 *

Title: Optimisation of landscape feature intelligent recognition algorithm based on deep learning

Keep up-to-date