As adaptive neuro-fuzzy inference system (ANFIS) has shown a high capability in solving various complicated problems, its usage has been increased so far. ANFIS is able to deal with large amounts of data with linear or nonlinear relations. In this paper, an ANFIS-based methodology was proposed in order to detect objects in complex city scenes using digital aerial images and LiDAR data. In this regard, four features were generated and normalized as ANFIS inputs. These features were Green band, normalized difference vegetation index (NDVI), and normalized digital surface model (nDSM) which was prepared using two different algorithms via morphological operations. Two objects were detected including buildings and trees. The proposed ANFIS used three different algorithms to build its fuzzy inference system structure including grid partition, subtractive clustering, and fuzzy c-means clustering. The results were evaluated on three different test areas provided by fourth working group of third commission (WG III/4) in the international society of photogrammetry and remote sensing (ISPRS), over Vaihingen in Germany, known as Area 1, Area 2 and Area 3. The achieved results were compared with each other together with ISPRS WG III/4 participants’ results by considering Completeness, Correctness and Quality indices in per-area and per-object levels. Comparisons demonstrated efficiency capability of ANFIS in detecting objects in complex city scenes in trees and buildings detection. For an instance in Area 3 area-based Completeness, Correctness, and Quality were 93.0%, 93.3% and 87.2% in building detection and 70.5%, 78.4% and 59.0% in tree detection.
کلید واژگان :Adaptice Neuro-Fuzzy Inference System, ANFIS, LiDAR, nDSM, Aerial Image, Object Detection
ارزش ریالی : 600000 ریال
با پرداخت الکترونیک