Video Footage Highlight Detection in Formula 1 Through Vehicle Recognition with Faster R-CNN Trained on Game Footage

Formula One, and its accompanying e-sports series, provides viewers with a large selection of camera angles, with the onboard cameras oftentimes providing the most exciting view of events. Through the implementation of three object detection pipelines, namely Haar cascades, Histogram of Oriented Gradient features with a Support Vector Machine, and a Faster Region-based Convolutional Neural Network (Faster R-CNN), we analyse their ability to detect the cars in real-life and virtual onboard footage using training images taken from the official F1 2019 video game. The results of this research concluded that Faster R-CNNs would be best suited for accurate detection of vehicles to identify events such as crashes occurring in real-time. This finding is evident through the precision and recall scores of 97% and 99%, respectively. The speed of detection when using a Haar cascade also makes it an attractive choice in scenarios where precise detection is not important. The Haar cascade achieved the lowest detection time of only 0.14 s per image at the cost of precision (71%). The implementation of HOG features classifier using an SVM was unsuccessful with regards to detection and speed, which took up to 17 s to classify an image. Both the Haar cascade and HOG feature models improved their performance when tested on real-life images (76% and 67% respectively), while the Faster R-CNN showed a slight drop in terms of precision (93%).

[1]  Qinghui Zhang,et al.  Research on Vehicle Object Detection Method Based on Convolutional Neural Network , 2018, 2018 11th International Symposium on Computational Intelligence and Design (ISCID).

[2]  Yang Yu,et al.  Real-time vehicle detection using histograms of oriented gradients and AdaBoost classification , 2016 .

[3]  Atouf Issam,et al.  Real-time Detection of Vehicles Using the Haar-like Features and Artificial Neuron Networks☆ , 2015 .

[4]  Sahaj Singh Maini,et al.  A Fast Video Image Detection using TensorFlow Mobile Networks for Racing Cars , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[5]  Faming Shao,et al.  Improved Faster R-CNN Traffic Sign Detection Based on a Second Region of Interest and Highly Possible Regions Proposal Network , 2019, Sensors.

[6]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  Xinkai Wu,et al.  A Hybrid Vehicle Detection Method Based on Viola-Jones and HOG + SVM from UAV Images , 2016, Sensors.

[8]  Margaret Lech,et al.  Object Recognition Using Deep Convolutional Features Transformed by a Recursive Network Structure , 2016, IEEE Access.

[9]  Milan Petkovic,et al.  Multi-modal extraction of highlights from TV Formula 1 programs , 2002, Proceedings. IEEE International Conference on Multimedia and Expo.

[10]  Wei Chen,et al.  A Fluorescence Inner-Filter Effect Based Sensing Platform for Turn-On Detection of Glutathione in Human Serum , 2019, Sensors.

[11]  Thambipillai Srikanthan,et al.  Real-Time Image Resizing Hardware Accelerator for Object Detection Algorithms , 2013, 2013 International Symposium on Electronic System Design.

[12]  Wei Liu,et al.  Towards accurate tiny vehicle detection in complex scenes , 2019, Neurocomputing.

[13]  Xuerui Dai,et al.  HybridNet: A fast vehicle detection system for autonomous driving , 2019, Signal Process. Image Commun..

[14]  Muhammad Sarfraz,et al.  Real Time Object Detection and Motion , 2009, 2009 Second International Conference in Visualisation.

[15]  Sun-Young Hwang,et al.  An improved Haar-like feature for efficient object detection , 2014, Pattern Recognit. Lett..