Stereo matching algorithm based on deep learning: A survey

Hamid, M. S.; Manap, Nurulfajar Abd; Hamzah, Rostam Affendi; Kadmin, A. F.

doi:10.1016/j.jksuci.2020.08.011

Cited by 36 publications

(25 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The crucial steps for the stereo matching algorithm can be illustrated in Figure 1. This formalization of the main steps also mentioned in several other works of literature([6]- [8]). It begins with The stereo vision algorithm begins with matching cost computation.…”

Section: Literature Reviewmentioning

confidence: 62%

“…The second step, cost aggregation, is responsible for decreasing the errors in the initial matching cost. As highlighted in our previous study [8], the edge-preserving filters such as bilateral filter (BF) [10] and guided filter (GF) [11] can achieve the purpose. These filters maintain a good edge while smoothing the input.…”

Section: Figure 1 Stereo Matching Algorithm Stepsmentioning

confidence: 96%

“…Layer 2 contains a fully connected (FC) layer or dense layer that produces 200 neurons. Similar to MC-CNN-acrt architecture mentioned in [8], the feature vectors from left and right are concatenated and supplied to the classification part. The next layer in the classification part, DEN4, is a fully connected layer or dense layer.…”

Section: Figure 5 Proposed Cnn Architecturementioning

confidence: 99%

“…Based on our previous literature [8], we employ a simple yet effective Winner-Take-All (WTA) optimization to compute the disparity map in this stage. As per the following Equation ( 7), WTA optimization will produce an initial disparity map, ( ).…”

Section: Disparity Computation / Optimizationmentioning

confidence: 99%

See 3 more Smart Citations

Stereo Matching Algorithm Based on Hybrid Convolutional Neural Network and Directional Intensity Difference

Hamid¹,

Manap²,

Hamzah³

et al. 2021

IJETAE

Self Cite

View full text Add to dashboard Cite

Fundamentally, a stereo matching algorithm produces a disparity map or depth map. This map contains valuable information for many applications, such as range estimation, autonomous vehicle navigation and 3D surface reconstruction. The stereo matching process faces various challenges to get an accurate result for example low texture area, repetitive pattern and discontinuity regions. The proposed algorithm must be robust and viable with all of these challenges and is capable to deliver good accuracy. Hence, this article proposes a new stereo matching algorithm based on a hybrid Convolutional Neural Network (CNN) combined with directional intensity differences at the matching cost stage. The proposed algorithm contains a deep learning-based method and a handcrafted method. Then, the bilateral filter is used to aggregate the matching cost volume while preserving the object edges. The Winner-Take-All (WTA) is utilized at the optimization stage which the WTA normalizes the disparity values. At the last stage, a series of refinement processes will be applied to enhance the final disparity map. A standard benchmarking evaluation system from the Middlebury Stereo dataset is used to measure the algorithm performance. This dataset provides images with the characteristics of low texture area, repetitive pattern and discontinuity regions. The average error produced for all pixel regions is 8.51%, while the nonoccluded region is 5.77%. Based on the experimental results, the proposed algorithm produces good accuracy and robustness against the stereo matching challenges. It is also competitive with other published methods and can be used as a complete algorithm

show abstract

Section: Literature Reviewmentioning

confidence: 62%

Section: Figure 1 Stereo Matching Algorithm Stepsmentioning

confidence: 96%

Section: Figure 5 Proposed Cnn Architecturementioning

confidence: 99%

Section: Disparity Computation / Optimizationmentioning

confidence: 99%

See 2 more Smart Citations

Stereo Matching Algorithm Based on Hybrid Convolutional Neural Network and Directional Intensity Difference

Hamid¹,

Manap²,

Hamzah³

et al. 2021

IJETAE

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, deep-learning algorithms have outperformed most classical feature algorithms that preceded them [7,17,24]. Deep learning algorithms require large sets of examples and ground truth outputs from which they automatically learn to extract a larger spectrum of complex and abstract features [2].…”

Section: Literature Reviewmentioning

confidence: 99%

Pornographic content classification using deep-learning

Tabone

Camilleri

Bonnici

et al. 2021

Proceedings of the 21st ACM Symposium on Document Engineering

View full text Add to dashboard Cite

Controlling the distribution of sensitive content such as pornography has become paramount with the ever-growing accessibility to the internet. Manual filtering of such large volumes of data is practically impossible, thus, the automatic detection of said material is sought after by Law Enforcement Agencies (LEAs) and has been tackled in various manners. However, the sorting of flagged pornographic documents is still done manually using scales that describe hierarchical degrees of content severity. In this paper, we address pornography detection by creating a model capable of locating and labelling sexual organs in images and extend this model to perform image classification to provide the user with one of 19 semantically meaningful descriptors of the content. Generating these descriptors serves as a proof of concept before approaching LEAs to work with illegal CSA material and scales such as COPINE. After creating our own custom sexual organ object detection dataset for the task at hand, we achieved an object detection mean average precision score of 63.63% and a top-3 classification accuracy of 87.78%. CCS CONCEPTS• Computing methodologies → Object detection.

show abstract

A Comparative Analysis of Pornography Detection Models to Prevent Gender Violence

Mishra,

Panda

2023

Signals and Communication Technology

View full text Add to dashboard Cite

Stereo matching algorithm based on deep learning: A survey

Cited by 36 publications

References 60 publications

Stereo Matching Algorithm Based on Hybrid Convolutional Neural Network and Directional Intensity Difference

Stereo Matching Algorithm Based on Hybrid Convolutional Neural Network and Directional Intensity Difference

Pornographic content classification using deep-learning

A Comparative Analysis of Pornography Detection Models to Prevent Gender Violence

Contact Info

Product

Resources

About