Automated labeling of training data for improved object detection in traffic videos by fine-tuned deep convolutional neural networks.
Iván García AguilarJorge García-GonzálezRafael Marcos Luque BaenaEzequiel López-RubioPublished in: Pattern Recognit. Lett. (2023)
Keyphrases
- fine tuned
- object detection
- convolutional neural networks
- training data
- fine tuning
- crowd sourced
- convolutional network
- domain specific
- scene understanding
- image parsing
- active learning
- decision trees
- learning algorithm
- machine learning
- data sets
- video frames
- test data
- video data
- unlabeled data
- face detection
- real time
- computer vision
- multiscale
- object recognition
- sample selection
- training set
- supervised learning
- training process
- road network
- network traffic
- training examples
- traffic flow
- support vector machine
- object segmentation
- video surveillance
- action detection
- key frames