Deep Learning vs. Traditional Computer Vision

Deep Learning has pushed the limits of what was possible in the domain of Digital Image Processing. However, that is not to say that the traditional computer vision techniques which had been undergoing progressive development in years prior to the rise of DL have become obsolete. This paper will analyse the benefits and drawbacks of each approach. The aim of this paper is to promote a discussion on whether knowledge of classical computer vision techniques should be maintained. The paper will also explore how the two sides of computer vision can be combined. Several recent hybrid methodologies are reviewed which have demonstrated the ability to improve computer vision performance and to tackle problems not suited to Deep Learning. For example, combining traditional computer vision techniques with Deep Learning has been popular in emerging domains such as Panoramic Vision and 3D vision for which Deep Learning models have not yet been fully optimised.

[1]  Kalyan Sunkavalli,et al.  Photometric Stabilization for Fast‐forward Videos , 2017, Comput. Graph. Forum.

[2]  Mohamed S. Shehata,et al.  Image Matching Using SIFT, SURF, BRIEF and ORB: Performance Comparison for Distorted Images , 2017, ArXiv.

[3]  Andreas Geiger,et al.  Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes , 2017, International Journal of Computer Vision.

[4]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[5]  Hassan Foroosh,et al.  Curvature Augmented Deep Learning for 3D Object Recognition , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[6]  Yanning Zhang,et al.  Convolutional Neural Network-Based Robot Navigation Using Uncalibrated Spherical Images , 2017, Sensors.

[7]  Torsten Sattler,et al.  Hybrid Scene Compression for Visual Localization , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Kiyoharu Aizawa,et al.  Significance of Softmax-Based Features in Comparison to Distance Metric Learning-Based Features , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Markus Vincze,et al.  Recurrent Convolutional Fusion for RGB-D Object Recognition , 2018, IEEE Robotics and Automation Letters.

[10]  Gim Hee Lee,et al.  PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[12]  Assaf Zeevi,et al.  The Hough transform estimator , 2004 .

[13]  Gunther Heidemann,et al.  Pixel-wise Ground Truth Annotation in Videos - An Semi-automatic Approach for Pixel-wise and Semantic Object Annotation , 2016, ICPRAM.

[14]  Tyler Highlander,et al.  Very Efficient Training of Convolutional Neural Networks using Fast Fourier Transform and Overlap-and-Add , 2016, BMVC.

[15]  Tyler Highlander.  Efficient Training of Small Kernel Convolutional Neural Networks using Fast Fourier Transform , 2015 .

[16]  Bodo Rosenhahn,et al.  Optical Flow-Based 3D Human Motion Estimation from Monocular Video , 2017, GCPR.

[17]  Ulrich Neumann,et al.  3D point cloud object detection with multi-view convolutional neural network , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[18]  Wil M. P. van der Aalst,et al.  Business Process Variability Modeling , 2017, ACM Comput. Surv..

[19]  Joseph Walsh,et al.  Improving controller performance in a powder blending process using predictive control , 2017, 2017 28th Irish Signals and Systems Conference (ISSC).

[20]  Dazhong Wu,et al.  Deep learning for smart manufacturing: Methods and applications , 2018, Journal of Manufacturing Systems.

[21]  Qi Tian,et al.  SIFT Meets CNN: A Decade Survey of Instance Retrieval , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Clara Fernandez-Labrador,et al.  Layouts From Panoramic Images With Geometry and Deep Learning , 2018, IEEE Robotics and Automation Letters.

[23]  George Konidaris,et al.  Hybrid Bayesian Eigenobjects: Combining Linear Subspace and Deep Network Methods for 3D Robot Vision , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[24]  Michael Felsberg,et al.  Image Alignment for Panorama Stitching in Sparsely Structured Environments , 2015, SCIA.

[25]  LinLin Shen,et al.  Hand-Crafted Feature Guided Deep Learning for Facial Expression Recognition , 2018, 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018).

[26]  Frank C. D. Tsai.  Geometric hashing with line features , 1994, Pattern Recognit..

[27]  Joseph Walsh,et al.  Adaptive process control and sensor fusion for process analytical technology , 2016, 2016 27th Irish Signals and Systems Conference (ISSC).

[28]  Laurent Wendling,et al.  Learning spatial relations and shapes for structural object description and scene recognition , 2018, Pattern Recognit..

[29]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[30]  Saeid Nahavandi,et al.  A Classifier Graph Based Recurring Concept Detection and Prediction Approach , 2018, Comput. Intell. Neurosci..

[31]  Arnaud Doucet,et al.  On the Selection of Initialization and Activation Function for Deep Neural Networks , 2018, ArXiv.

[32]  Yin Zhou,et al.  VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[33]  Mohamed S. Shehata,et al.  Image Identification Using SIFT Algorithm: Performance Analysis against Different Image Deformations , 2017, ArXiv.

[34]  Padhraic Smyth,et al.  Learning Priors for Invariance , 2018, AISTATS.

[35]  Lorenzo Torresani,et al.  Learning Spatiotemporal Features with 3D Convolutional Networks , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[36]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.

[37]  Mohak Shah,et al.  Comparative Study of Deep Learning Software Frameworks , 2015, 1511.06435.

[38]  Stefan Winkler,et al.  Deep Learning for Emotion Recognition on Small Datasets using Transfer Learning , 2015, ICMI.

[39]  Nikolaos Doulamis,et al.  Deep Learning for Computer Vision: A Brief Review , 2018, Comput. Intell. Neurosci..

[40]  Yiannis Kompatsiaris,et al.  Deep Learning Advances in Computer Vision with 3D Data , 2017, ACM Comput. Surv..

[41]  Marco Gori,et al.  Integrating Prior Knowledge into Deep Learning , 2017, 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA).

[42]  Tom Drummond,et al.  A review of deep learning in the study of materials degradation , 2018, npj Materials Degradation.

[43]  Katsushi Ikeuchi,et al.  Scene Understanding by Reasoning Stability and Safety , 2015, International Journal of Computer Vision.

[44]  Xun Cao,et al.  The role of prior in image based 3D modeling: a survey , 2017, Frontiers of Computer Science.

[45]  Graham W. Taylor,et al.  Dataset Augmentation in Feature Space , 2017, ICLR.

[46]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[47]  Cordelia Schmid,et al.  Modeling Visual Context is Key to Augmenting Object Detection Datasets , 2018, ECCV.

[48]  Nouar AlDahoul,et al.  Real-Time Human Detection for Aerial Captured Video Sequences via Deep Models , 2018, Comput. Intell. Neurosci..

[49]  Conor Ryan,et al.  Deep Learning for Visual Navigation of Unmanned Ground Vehicles : A review , 2018, 2018 29th Irish Signals and Systems Conference (ISSC).

[50]  Zhong Liu,et al.  A Novel Ensemble Method for Imbalanced Data Learning: Bagging of Extrapolation-SMOTE SVM , 2017, Comput. Intell. Neurosci..

[51]  Balasubramanian Raman,et al.  A hybrid of deep learning and hand-crafted features based approach for snow cover mapping , 2018, International Journal of Remote Sensing.

[52]  Francesco Visin,et al.  A guide to convolution arithmetic for deep learning , 2016, ArXiv.

[53]  Gary Marcus,et al.  Deep Learning: A Critical Appraisal , 2018, ArXiv.

[54]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[55]  Yijie Wang,et al.  High Performance Implementation of 3D Convolutional Neural Networks on a GPU , 2017, Comput. Intell. Neurosci..

[56]  Xiaohui Liu,et al.  A Composite Model of Wound Segmentation Based on Traditional Methods and Deep Neural Networks , 2018, Comput. Intell. Neurosci..

[57]  Bruno Feijó,et al.  Real time 360° video stitching and streaming , 2016, SIGGRAPH Posters.

[58]  Peter V. Gehler,et al.  Teaching 3D geometry to deformable part models , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[59]  Joseph Walsh,et al.  Real-time monitoring of powder blend composition using near infrared spectroscopy , 2017, 2017 Eleventh International Conference on Sensing Technology (ICST).