Chunsun Zhang's research while affiliated with RMIT University and other places

Publications (41)

Conference Paper
Full-text available
Automated building detection has been an active topic in photogrammetry and computer vision. One of the challenges is to effectively separate buildings from trees using aerial imagery and Lidar data. In cases where an adopted building detection technique cannot distinguish between these two classes of objects, the presence of trees in the scene can...
Article
The development of robust and accurate filtering approaches for automated extraction of digital terrain models (DTMs) from airborne Light Detection and Ranging (LiDAR) data continues to be a challenge. The problem is due to the nature of LiDAR point clouds, the complexity of scene components, and the intrinsic structure of the terrain itself. This...
Article
This letter presents a novel approach to automated extraction of roof planes from airborne light detection and ranging data based on spectral clustering of straight-line segments. The straight-line segments are derived from laser scan lines, and 3-D line geometry analysis is employed to identify coplanar line segments so as to avoid skew lines in p...
Article
Automatic registration of multisensor data, for example, imagery and Light Detection And Ranging (LiDAR), is a basic step in data fusion in the field of geospatial information processing. Mutual information (MI) has recently attracted research attention as a statistical similarity measure for intensity-based registration of multisensor images in th...
Conference Paper
The development of robust and accurate filtering approach for automated extraction of digital terrain model from airborne LiDAR data continues to be a challenge. The problem is due to the nature of LiDAR point cloud, the complexity of scene components, and the intrinsic structure of terrain itself. This paper proposes a novel approach for filtering...
Conference Paper
Full-text available
Geometric and radiometric attributes of targets are provided by full-waveform LiDAR data. However, the accuracy of such information depends largely on the adopted data processing method. In this study, the emphasis is on the retrieval of the temporal target cross-section by regularization methods, with the subsequent extraction of the backscatterin...
Conference Paper
Full-text available
Accurate waveform restoration, from the received noisy waveform, is of great interest to the full-waveform LiDAR community. As a result of this, important attributes could be estimated precisely which are valuable in describing and differentiating LiDAR targets. Assumptions behind prominent methods like the Gaussian decomposition do not hold due to...
Article
The development of robust and accurate methods for automatic registration of optical imagery and 3D LiDAR data continues to be a challenge for a variety of applications in photogrammetry, computer vision and remote sensing. This paper proposes a new approach for the registration of optical imagery with LiDAR data based on the theory of Mutual Infor...
Conference Paper
Full-text available
The lack of noise reduction methods resistant to waveform distortion can hamper correct and accurate decomposition in the processing of full-waveform LiDAR data. This paper evaluates a time-domain method for smoothing and reducing the noise level in such data. The Savitzky-Golay (S-G) approach approximates and smooths data by taking advantage of fi...
Book
Full-text available
Automatic registration of multi-sensor data is a basic step in data fusion for photogrammetric and remote sensing applications. The effectiveness of intensity-based methods such as Mutual Information (MI) for automated registration of multi-sensor image has been previously reported for medical and remote sensing applications. In this paper, a new m...
Conference Paper
Full-text available
Accurate range determination and retrieval of the cross section are two important issues in the processing of full-waveform LiDAR data, especially between closely located targets. The dependency of the received waveform on the emitted pulse can be removed through deconvolution and consequently comparisons between waveforms recorded by different sen...
Conference Paper
Full-text available
Automatic registration of multi-sensor data is a basic step in data fusion applications. Mutual information (MI) has been widely used in medical and remote sensing image registration. In this paper, an effective histogram binning technique is proposed to improve the robustness of image registration using MI and Normalized MI (NMI). Increasing the b...
Article
Full-text available
Automatic 3D extraction of building roofs from remotely sensed data is important for many applications including city modelling. This paper proposes a new method for automatic 3D roof extraction through an effective integration of LIDAR (Light Detection And Ranging) data and multispectral orthoimagery. Using the ground height from a DEM (Digital El...
Conference Paper
Full-text available
Automatic co-registration is a basic step in multi-sensor data fusion for remote sensing applications. The effectiveness of Mutual Information (MI) as a similarity measure for multisensor image registration has previously been reported for medical and remote sensing applications. In this paper, a new intensity-based approach built on local MI princ...
Article
Full-text available
The performance of automatic building detection techniques can be significantly impeded due to the presence of same-height objects, for example, trees. Consequently, if a building detection technique cannot distinguish between trees and buildings, both its false positive and false negative rates rise significantly. This paper presents an improved a...
Conference Paper
Full-text available
Automatic image registration is a basic step in multi-sensor data integration in remote sensing and photogrammetric operations such as data fusion. The effectiveness of intensity-based methods for automated multi-sensor image registration, such as Mutual Information (MI) and the Correlation Ratio (CR), have previously been demonstrated for medical...
Conference Paper
Full-text available
Automatic image registration is a basic step in multi-sensor data integration in remote sensing and photogrammetric applications such as data fusion. The effectiveness of Mutual Information (MI) as a technique for automated multi-sensor image registration has previously been demonstrated for medical and remote sensing applications. In this paper, a...
Article
Full-text available
Effective separation of buildings from trees is a major challenge in image-based automatic building detection. This paper presents a three-step method for effective separation of buildings from trees using aerial imagery and lidar data. First, it uses cues such as height to remove objects of low height such as bushes, and width to exclude trees wit...
Conference Paper
Full-text available
The success of automatic building detection techniques lies in the effective separation of buildings from trees. This paper presents an improved automatic building detection technique that achieves more effective separation of buildings from trees. Firstly, it uses cues such as height to remove objects of low height such as bushes, and width to exc...
Article
Road condition data are important in transportation management systems. Over the last decades, significant progress has been made and new approaches have been proposed for efficient collection of pavement condition data. However, the assessment of unpaved road conditions has been rarely addressed in transportation research. Unpaved roads constitute...
Conference Paper
Full-text available
Automatic D reconstruction of building roofs from remotely sensed data is important for many applications including automatic city modeling. This paper proposes a new method for automatic roof reconstruction using LIDAR (Light Detection And Ranging) data and multispectral imagery. Using the ground height from a DEM (Digital Elevation Model), the ra...
Article
This paper reports on the application of a generic physical sensor orientation model for evaluation of the georeferencing performance of 2 m resolution imagery from the Thailand Earth Observation System (THEOS) satellite. Within the generic sensor orientation model, orbit and attitude data are employed to describe the satellite trajectory, which is...
Article
Full-text available
Since January 2008, the U.S. Department of Interior / U.S. Geological Survey have been providing free terrain-corrected (Level 1T) Landsat Enhanced Thematic Mapper Plus (ETM+) data via the Internet, currently for acquisitions with less than 40% cloud cover. With this rich dataset, temporally composited, mosaics of the conterminous United States (CO...
Article
Full-text available
This paper describes the developed techniques for photogrammetric orientation of imagery acquired from a low-altitude Unmanned Aerial Vehicle (UAV) platform in a project for rural road condition monitoring. After feature points are extracted in images, conjugate feature points are determined across images by comparing point attributes. Then, automa...
Article
Full-text available
Road condition data are very important in transportation management system. Conventional data collection approach is time-consuming and labor intensive. This paper reports the developed techniques for 3D road surface reconstruction in support of unpaved road distress assessment using imagery acquired from a Unmanned Aviation Vehicle (UAV)-based ima...
Article
We present an Unmanned Aviation Vehicle-based Photogrammetric mapping system in this paper. This work is part of a project monitoring of unpaved road condition using remote sensing and other technology, sponsored by the US Department of Transportation. The system is based on a low cost model helicopter equipped with a GPS/IMU and a geomagnetic sens...
Article
Full-text available
Automated processes in commercial-off-the-shelf (COTS) systems are increasingly prevalent as new technology, and new knowledge is fused to enhance accessibility to spatial information. Automated terrain extraction is becoming a standard capability implemented into photogrammetric software. This paper focuses on digital surface model (DSM) generatio...
Article
Automatic registration of remotely sensed imagery is an important technique in GIS as geographical databases need to undergo frequent updating due to rapid changes in the physical environment. While satellite imagery, with its recently enhanced spatial, spectral and temporal resolution, allows for accurate and reliable detection and characterisatio...
Article
Accurate 3D road network is a vital component of GIS for many applications, including traffic management, monitoring, city modeling, and visualization. This paper presents a practical system for automated 3D road network reconstruction by integrated processing of color image data and information from existing digital spatial databases. Starting fro...
Article
Full-text available
Change detection is important for an up-to-date GIS database. The ever improving spatial, spectral and temporal resolution of satellite imagery allows for reliable detection and characterization of even more details of the changed patterns with higher accuracy. The quality of registration of the involved imagery is the key factor that dictates the...
Article
The extraction of road networks from aerial images is one of the current challenges in digital photogrammetry and computer vision. In this paper, we present a practical system for 3-D road network reconstruction from aerial images using knowledge-based image analysis. In contrast to other approaches, the developed system integrates processing of co...
Article
This paper presents a practical system for automated 3-D road network reconstruction from aerial images using knowledge-based image analysis. The system integrates processing of color image data and information from digital spatial databases, extracts and fuses multiple object cues, takes into account context information, employs existing knowledge...
Article
The extraction of road networks from aerial images is one of the current challenges in digital photogrammetry and computer vision. In this paper, we present our system for 3D road network reconstruction from aerial images using knowledge-based image analysis. In contrast to other approaches, the developed system integrates processing of color image...
Article
An approach to achieve automated road network detection from digital images is presented. The method is based on mathematical morphology analysis while most road extraction algorithms are based on linear analysis methods. As the image resolution increases, road networks appear to be areas with certain width rather than thin lines. The approach prop...
Article
Full-text available
The extraction of road networks from aerial images is one of the current challenges in digital photogrammetry and computer vision. In this paper, we present our developed system for 3D road network reconstruction from aerial images using knowledgebased image analysis. In contrast to other approaches, the developed system integrates knowledge proces...
Article
In this paper, we present a knowledge-base d system for automatic extraction of 3D roads from two or more aerial images which integrates processing of colour image data and existing digital spatial databases. The information of the existing road database provides a rough model of the scene. Color aerial images give the current situation of the scen...
Article
Road network extraction from aerial images has received attention in photogrammetry and computer vision for decades. We present a concept for road network reconstruction from aerial images using knowledge-based image analysis. In contrast to other approaches, the proposed approach uses multiple cues about the object existence, employs existing know...
Article
Full-text available
Terrain deformation data is utilized in many applications including geological hazard monitoring and modeling. In particular, these data play an important role in tectonic deformation modeling and are being used to study the coseismic and postseismic processes of the 2004/2005 earthquake events associated with the Sumatra-Andaman Subduction Zone (S...
Article
Full-text available
The Thailand Earth Observation System (THEOS) satellite, launched in October 2008, provides 2m resolution imagery worldwide. Camera parameters, orbit and attitude data suited to rigorous sensor orientation modelling are provided with the imagery. However, RPCs for direct object-to-image space transformation are not currently generated. This paper r...
Article
This paper discusses an Unmanned Aviation Vehicle (UAV)-based remote sensing system for unpaved road condition assessment. The reported work has been part of the project "Monitoring of Unpaved Road Condition using Remote Sensing and Other Technology", sponsored by the US Department of Transportation. The system is based on a low cost model helicopt...

Citations

... In order to retrieve the target response from waveforms, a robust deconvolution method based upon sparsity-based regularization (Azadbakht et al. 2014;Azadbakht et al. 2015) is applied to the received waveforms. Similar to other deconvolution methods, it does not demand the number of returns in advance and requires no assumption on the shape of pulses (Roncat et al. 2011;Wu et al. 2011). ...
... assessment in a large area (Patino & Duque, 2013). The automatic extraction of buildings from high-resolution satellite imagery has been studied by many researchers from different perspectives, such as object-oriented segmentation, semantic segmentation, and edge detection (Ahmadi et al., 2010;Dash et al., 2004;Ghanea et al., 2014;Xia et al., 2019;C. Zhang et al., 2012). The Deep Encoding Network (DE-Net) proposed by Liu et al. (2019) typically yields a higher building extraction precision than traditional models and is less affected by noise, such as building roof color changes or tree coverage . Considering the high efficiency of DE-Net in building identification in mountainous areas, the combination ...
... These methods basically rely on the erosion operator to implement mathematical morphology. Although computation efficiency and processing time are improved in these methods, issues such as gradual parameter selection for the morphological filter in different land covers and poor performance in sparse point clouds are still consistent [26,27]. ...
... Notarangelo et al. (2021) used high-resolution raster digital surface model (DSM) data to extract buildings, and their research results showed that the use of only high-resolution raster DSM data to extract buildings could achieve high accuracy. Several scholars used radar data to extract the top surface of buildings using methods such as classification, filtering, segmentation, clustering and interpolation to achieve the highest extraction accuracy of 95% (Zhu et al., 2006;Li et al., 2016;Zhao et al., 2017;Gilani et al., 2018;Zhang et al., 2018). Schlosser et al. (2020) combined spectral band with texture data to extract buildings using machine learning technologies, and through feature selection, the building extraction accuracy exceeded 95% at the pixel level. ...
... The developed methodology takes more time for constructing graph in order to identify the differences in remote sensing image. Parmehr et al. (2016) presented a bin size selection approach to improve registration reliability. The advanced technique established the superior (uniform) bin size for the pdf calculation and an examination of the relationship among the similarity estimate values of the information. ...
... Advances in light detection and ranging (LiDAR) technology have produced accurate terrain altitude with airborne laser scanning (ALS). Many scientific studies use ground elevation and canopy heights in various applications such as urban environment mapping of Land Use and Land Cover (LULC) [1][2][3], extracting objects such as buildings [4], estimating urban tree canopy and heights [5,6], detecting roads [7], modeling floods and wetlands [8,9], quantifying urban landscape changes under a historical perspective [10], and investigating the Digital Elevation Model (DEM) generation process and upward fusion with another more generic DEM [11,12]. One problem is the high cost of ALS, with surveys covering small areas. ...
... In the process of extracting contour lines, other point clouds such as vegetation will greatly interfere with the results. So, first of all, the point cloud data of tree and ground will be removed [24]. Afterward, the triangle inside the obtained contour line is separated from the original model, and a new model is constructed. ...
... Wefelscheid et al. (2011) used an octo-copter (1.5 kg weight and payload of 500 g) for 3D reconstruction of buildings through a consumer camera with prime lens and weight of 285 g. Melgani (2014a and2014b) used an UAV for automatic detection of cars in visible images, captured by a commercial camera. Feature extraction and machine learn- ing based on support vector machines were the approaches used. ...
... The metadata file contains the orbit, attitude and the camera parameters data. These metadata are similar to SPOT5, Formosat2 and Theos metadata [20] Based on the analysis of the metadata provided with ALSAT-2A, the rigorous pushbroom camera model can be developed. This model has been successfully applied to many very high resolution imagery systems [5], [8]- [11]. ...
... These methods utilize images to reconstruct three-dimensional models of the distress. The techniques themselves are not new and there have been previous attempts to incorporate them into pavement distress applications [14][15][16][17]. However, criticisms have been made which include limitations with respect to accuracy, computational requirements and software availability. ...