Latent Constrained Correlation Filter

Zhang, Baochang; Luan, Shangzhen; Chen, Chen; Han, Jungong; Wang, Wei; Perina, Alessandro; Shao, Ling

doi:10.1109/tip.2017.2775060

Cited by 44 publications

(27 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The extensive experiments show that GCNs significantly improved baselines, resulting in the state-of-theart performance over several benchmarks. In the future, more GCNs architectures (larger ones) will be tested on other tasks, such as object tracking, detection and segmentation [41], [42], [43], [44]. …”

Section: E Experiments On Food-101 Datasetmentioning

confidence: 99%

Gabor Convolutional Networks

Luan

Chen

Zhang

et al. 2018

IEEE Trans. on Image Process.

Self Cite

278

103

View full text Add to dashboard Cite

Abstract-In steerable filters, a filter of arbitrary orientation can be generated by a linear combination of a set of "basis filters". Steerable properties dominate the design of the traditional filters e.g., Gabor filters and endow features the capability of handling spatial transformations. However, such properties have not yet been well explored in the deep convolutional neural networks (DCNNs). In this paper, we develop a new deep model, namely Gabor Convolutional Networks (GCNs or Gabor CNNs), with Gabor filters incorporated into DCNNs such that the robustness of learned features against the orientation and scale changes can be reinforced. By manipulating the basic element of DCNNs, i.e., the convolution operator, based on Gabor filters, GCNs can be easily implemented and are readily compatible with any popular deep learning architecture. We carry out extensive experiments to demonstrate the promising performance of our GCNs framework and the results show its superiority in recognizing objects, especially when the scale and rotation changes take place frequently. Moreover, the proposed GCNs have much fewer network parameters to be learned and can effectively reduce the training complexity of the network, leading to a more compact deep learning model while still maintaining a high feature representation capacity. The source code can be found at https://github.com/bczhangbczhang .

show abstract

Section: E Experiments On Food-101 Datasetmentioning

confidence: 99%

Gabor Convolutional Networks

Luan

Chen

Zhang

et al. 2018

IEEE Trans. on Image Process.

Self Cite

278

103

View full text Add to dashboard Cite

show abstract

“…A group of metrics including accuracy, recall and precision were employed to quantify the classification accuracy. The definition of accuracy, recall, and precision are described as Equations (2)–(4), where true positive (TP), true negative (TN), false positive (FP), and false negative (FN) are labeled in Figure 4 [ 38 ].

…”

Section: Resultsmentioning

confidence: 99%

“…Since Hinton [ 35 , 36 ] proposed a greedy layer-wise pre-training algorithm to initialize the weights of deep architectures, artificial neural networks have been revived. Deep neural networks have become a new popular topic and advanced in image classification, object tracking [ 37 ] and recognition [ 38 ], gesture recognition [ 39 ], action recognition [ 40 ], defect inspection [ 41 , 42 , 43 , 44 ], voice recognition, natural language understanding, etc. Popular deep learning frameworks include stacked autoencoders, convolutional neural networks, and restricted Boltzmann machine.…”

Section: Proposed Methodsmentioning

confidence: 99%

Pixel-Wise Crack Detection Using Deep Local Pattern Predictor for Robot Application

Wang

2018

Sensors

View full text Add to dashboard Cite

Robotic vision-based crack detection in concrete bridges is an essential task to preserve these assets and their safety. The conventional human visual inspection method is time consuming and cost inefficient. In this paper, we propose a robust algorithm to detect cracks in a pixel-wise manner from real concrete surface images. In practice, crack detection remains challenging in the following aspects: (1) detection performance is disturbed by noises and clutters of environment; and (2) the requirement of high pixel-wise accuracy is difficult to obtain. To address these limitations, three steps are considered in the proposed scheme. First, a local pattern predictor (LPP) is constructed using convolutional neural networks (CNN), which can extract discriminative features of images. Second, each pixel is efficiently classified into crack categories or non-crack categories by LPP, using as context a patch centered on the pixel. Lastly, the output of CNN—i.e., confidence map—is post-processed to obtain the crack areas. We evaluate the proposed algorithm on samples captured from several concrete bridges. The experimental results demonstrate the good performance of the proposed method.

show abstract

“…Algorithm 2 Dijkstra-distance Based Correlation Filters 1: Set t = 0, ε best = +∞, η = 0.7 (suggested in [35]…”

Section: Methodsmentioning

confidence: 99%

Object detection and tracking benchmark in industry based on improved correlation filter

Luan

Wang

et al. 2018

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Real-time object detection and tracking have shown to be the basis of intelligent production for industrial 4.0 applications. It is a challenging task because of various distorted data in complex industrial setting. The correlation filter (CF) has been used to trade off the low-cost computation and high performance. However, traditional CFtraining strategy can not get satisfied performance for the various industrial data; because the simple sampling(bagging) during training process will not find the exact solutions in a data space with a large diversity. In this paper, we propose Dijkstra-distance based correlation filters (DBCF), which establishes a new learning framework that embeds distribution-related constraints into the multi-channel correlation filters (MCCF). DBCF is able to handle the huge variations existing in the industrial data by improving those constraints based on the shortest path among all solutions. To evaluate DBCF, we build a new dataset as the benchmark for industrial 4.0 application. Extensive experiments demonstrate that DBCF produces high performance and exceeds the state-of-the-art methods.The dataset and source code can be found at https://github.com/bczhangbczhang.

show abstract

Latent Constrained Correlation Filter

Cited by 44 publications

References 39 publications

Gabor Convolutional Networks

Gabor Convolutional Networks

Pixel-Wise Crack Detection Using Deep Local Pattern Predictor for Robot Application

Object detection and tracking benchmark in industry based on improved correlation filter

Contact Info

Product

Resources

About