Urban forests are vital in urban areas because they clean the air, absorb water, and protect the environment from intense heat. Destruction of the urban forest by increased urbanization is a considerable threat to the ecosystem. Hence, urban planners must obtain and manage information about urban forests, but the complexity of urban areas has made these tasks difficult. With developments in remote-sensing technologies, the monitoring and detection of urban forests can be achieved without performing any field measurements. In this study, different remote-sensing imageries and various methods are evaluated to obtain urban forest information. This review demonstrates that very high resolution (VHR) satellite imagery, such as from WorldView-2, is the most efficient data that can be used to obtain urban forest information. The use of the combination of LiDAR data with VHR imagery increases the accuracy of information, particularly about tree crown delineation. Traditional pixel-based classification methods are not effectively applicable to obtain urban tree information because of significant spectral variability in urban areas. An object-based classification technique, which uses spatial, textural, and color information, can be a potential method to detect urban forest and tree species discrimination. The new VHR imaging method, which uses the object-based technique, is recommended to overcome limitations of collecting urban forest information.

The sustainable management and monitoring of urban forests is an important activity in the urbanized world, and operational approaches require information about the status of urban trees to determine the best strategy. One limitation in urban forest studies is the detection and discrimination of tree species using limited training data. Thus, this study focuses on developing generic rule sets from high-resolution WorldView-2 imagery in conjunction with spectral, spatial, colour and textural information for automated urban tree species detection. The object-based image analysis and its combination with statistical analysis of object features is utilized for this purpose. Results of attribute selection indicated that from 55 attributes, only 26 were useful to discriminate urban tree species, namely Messua ferrea L., Samanea saman and Casuarina sumatrana. Finally, the high overall accuracy, approximately 86.87% with kappa of 0.75 confirmed the transferability of the generic model.