Semi-automatic extraction of road networks by least squares interlaced template matching in urban areas

Lin, Xiangguo; Zhang, Jixian; Liu, Zhengjun; Shen, Jing; Duan, Minyan

doi:10.1080/01431161.2010.493565

Cited by 34 publications

(32 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Template-matching based approaches are often used in extracting objects in imagery . Lin et al (2011) proved that line-shaped lane markings or median strips are less impacted by disturbances of vehicles or shadows of trees than any other parts in imagery. A least-squares template matching is utilized to search the centre line points.…”

Section: Introductionmentioning

confidence: 98%

Road network extraction: a neural-dynamic framework based on deep learning and a finite state machine

Wang

Song

Chen

et al. 2015

International Journal of Remote Sensing

143

View full text Add to dashboard Cite

Extracting road networks from very-high-resolution (VHR) aerial and satellite imagery has been a long-standing problem. In this article, a neural-dynamic tracking framework is proposed to extract road networks based on deep convolutional neural networks (DNN) and a finite state machine (FSM). Inspired by autonomous mobile systems, the authors train a DNN to recognize the pattern of input data, which is an image patch extracted in a detection window centred at the current location of the tracker. The pattern is predefined according to the environment and associated with the states in the FSM. A vector-guided sampling method is proposed to generate the training data set for the DNN, which extracts massive image-direction pairs from the imagery and existing vector road maps. In the tracking procedure, the size of the detection window is determined by a fusion strategy and the extracted image patches represent the orientation features of the road (local environment) that can be recognized by the trained DNN. The reactive unit in FSM associates states with behaviours of the tracker while continually modifying the orientation to follow the road and generating a sequence of states and locations. In this way, our framework combines the DNN and FSM. DNN acts as a key component to recognize patterns from a complex and changing environment; FSM translates the recognized patterns to states and controls the behaviour of the tracker. The results illustrate that our approach is more accurate and efficient than the traditional ones.

show abstract

Section: Introductionmentioning

confidence: 98%

Road network extraction: a neural-dynamic framework based on deep learning and a finite state machine

Wang

Song

Chen

et al. 2015

International Journal of Remote Sensing

143

View full text Add to dashboard Cite

show abstract

“…Interlaced window is composed of two parts: some cross-section profiles (i.e., each is a typical intensity profile perpendicular and symmetrical to the road axis) and some rectangular windows of road markings (i.e., some intensity rectangles whose width is as wide as lane markings). Lin et al [13] used interlaced window to predict next most possible position of the road axis. However, the windows mentioned above cannot adapt to different width road detection because of fixed size.…”

Section: Local Detectionmentioning

confidence: 99%

“…Numerous semiautomatic road extraction methods have been proposed from high-resolution remote sensing images [8][9][10][11][12][13][14], which are usually categorized into iterative two phases: local detection and global tracking. The local detection contents mainly include direction, width, and central point position in current local road region.…”

Section: Introductionmentioning

confidence: 99%

Road Extraction from High-Resolution SAR Images via Automatic Local Detecting and Human-Guided Global Tracking

Cheng

Ding

et al. 2012

International Journal of Antennas and Propagation

View full text Add to dashboard Cite

Because of existence of various kinds of disturbances, layover effects, and shadowing, it is difficult to extract road from high-resolution SAR images. A new road center-point searching method is proposed by two alternant steps: local detection and global tracking. In local detection step, double window model is set, which consists of the outer fixed square window and the inner rotary rectangular one. The outer window is used to obtain the local road direction by using orientation histogram, based on the fact that the surrounding objects always range along with roads. The inner window rotates its orientation in accordance with the result of local road direction calculation and searches the center points of a road segment. In global tracking step, particle filter of variable-step is used to deal with the problem of tracking frequently broken by shelters along the roadside and obstacles on the road. Finally, the center-points are linked by quadratic curve fitting. In 1 m high-resolution airborne SAR image experiment, the results show that this method is effective.

show abstract

“…Commonly used variable templates include dynamic contour models [30][31][32][33] and level set models [30]. Rule templates include profile templates [34,35], rectangular templates [36], and T-shaped templates [37]. For example, Zhang et al [38] manually input three points on both sides of a road, constructed a rectangular template and input direction parameter information, used the gray difference and Euclidean distance as the similarity measure to determine the best tracking results, and completed the extraction of the road network using the iterative method.…”

Section: Introductionmentioning

confidence: 99%

Lane-Level Road Extraction from High-Resolution Optical Satellite Images

et al. 2019

View full text Add to dashboard Cite

High-quality updates of road information play an important role in smart city planning, sustainable urban expansion, vehicle management, urban planning, traffic navigation, public health and other fields. However, due to interference from road geometry and texture noise, it is difficult to avoid the decline of automation while accurately extracting roads. Therefore, we propose a high-resolution optical satellite image lane-level road extraction method. First, from the perspective of template matching and considering road characteristics and relevant semantic relations, an adaptive correction model, an MLSOH (multi-scale line segment orientation histogram) descriptor, a sector descriptor, and a multiangle beamlet descriptor are proposed to solve the interference from geometry and texture noise in road template matching and tracking. Second, based on refined lane-level tracking, single-lane and double-lane road-tracking modes are designed to extract single-lane and double-lane roads, respectively. In this paper, Pleiades satellite and GF-2 images are selected to set up different scenarios for urban and rural areas. Experiments are carried out on the phenomena that restrict road extraction, such as tree occlusion, building shadow occlusion, road bending, and road boundary blurring. Compared with other methods, the proposed method not only ensures the accuracy of lane-level road extraction but also greatly improves the automation of road extraction.

show abstract

Semi-automatic extraction of road networks by least squares interlaced template matching in urban areas

Cited by 34 publications

References 19 publications

Road network extraction: a neural-dynamic framework based on deep learning and a finite state machine

Road network extraction: a neural-dynamic framework based on deep learning and a finite state machine

Road Extraction from High-Resolution SAR Images via Automatic Local Detecting and Human-Guided Global Tracking

Lane-Level Road Extraction from High-Resolution Optical Satellite Images

Contact Info

Product

Resources

About