Straight road edge detection from high-resolution remote sensing images based on the ridgelet transform with the revised parallel-beam Radon transform

Li, Xiaofeng; Zhang, Shuqing; Pan, Xin; Dale, Pat; Cropp, Roger Allan

doi:10.1080/01431160903283835

Cited by 41 publications

(27 citation statements)

References 26 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the early studies, most methods employed unsupervised models to detect targets in RSIs [1][2][3][4][5][6], which mainly depended on the features used in their models and may be effective for detecting targets with simple appearance and small variations.…”

Section: Introductionmentioning

confidence: 99%

Negative Bootstrapping for Weakly Supervised Target Detection in Remote Sensing Images

Zhou

Zhang

Cheng

et al. 2015

2015 IEEE International Conference on Multimedia Big Data

View full text Add to dashboard Cite

When training a classifier in a traditional weakly supervised learning scheme, negative samples are obtained by randomly sampling. However, it may bring deterioration or fluctuation for the performance of the classifier during the iterative training process. Considering a classifier is inclined to misclassify negative examples which resemble positive ones, comprising these misclassified and informative negatives should be important for enhancing the effectiveness and robustness of the classifier. In this paper, we propose to integrate Negative Bootstrapping scheme into weakly supervised learning framework to achieve effective target detection in remote sensing images. Compared with traditional weakly supervised target detection schemes, this method mainly has three advantages. Firstly, our model training framework converges more stable and faster by selecting the most discriminative training samples. Secondly, on each iteration, we utilize the negative samples which are most easily misclassified to refine target detector, obtaining better performance. Thirdly, we employ a pre-trained convolutional neural network (CNN) model named Caffe to extract high-level features from RSIs, which carry more semantic meanings and hence yield effective image representation. Comprehensive evaluations on a high resolution airplane dataset and comparisons with state-of-the-art weakly supervised target detection approaches demonstrate the effectiveness and robustness of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

Negative Bootstrapping for Weakly Supervised Target Detection in Remote Sensing Images

Zhou

Zhang

Cheng

et al. 2015

2015 IEEE International Conference on Multimedia Big Data

View full text Add to dashboard Cite

show abstract

“…Zhang and Couloigner (2007) investigated the peak selection problem in the line detector and proposed a mean filter to locate the true peak in the Radon image. Li et al (2010) proposed the revised parallel-beam Radon transform by solving the problem of the false maximum of the coefficients in the Radon domain. Although straight road edges can be extracted successfully by these algorithms; there are still difficulties in processing complicated images.…”

Section: Introductionmentioning

confidence: 99%

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

147

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

“…In many applications, it is enough to get the periphery of the object, which is called "edge enhancement" in image processing. However, poor imaging quality of GI limits the edge detection, which is important for target recognition and localization in remote sensing and biological imaging [12][13][14]. Recently, there have been two main ways to solve this problem.…”

Section: Introductionmentioning

confidence: 99%

Speckle-Shifting Ghost Imaging

Mao

Chen

et al. 2016

IEEE Photonics J.

View full text Add to dashboard Cite

Abstract:In this paper, we introduce speckle-shifting ghost imaging (SSGI), which uses several corresponding shifted groups of speckle patterns instead of random speckle patterns in "computational ghost imaging" (CGI) to improve the performance of edge detection. The shifting of speckle patterns makes SSGI directly achieve the edges of an unknown object without the clear "ghost" images. Numerical simulations and experiments are performed. It is seen that SSGI is applicable for both binary and gray-scale objects in noisy environments. This provides the great opportunity to pave the way for real applications of CGI in remote sensing and biological imaging.

show abstract

Straight road edge detection from high-resolution remote sensing images based on the ridgelet transform with the revised parallel-beam Radon transform

Cited by 41 publications

References 26 publications

Negative Bootstrapping for Weakly Supervised Target Detection in Remote Sensing Images

Negative Bootstrapping for Weakly Supervised Target Detection in Remote Sensing Images

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

Speckle-Shifting Ghost Imaging

Contact Info

Product

Resources

About