$$\text{C}^{3}\text{Net}$$ C 3 Net : end-to-end deep learning for

            : end-to-end deep learning for },
  author={C. Kyrkou},
  journal={Journal of Real-Time Image Processing},
  • C. Kyrkou
  • Published 2021
  • Computer Science
  • Journal of Real-Time Image Processing
The need for automated real-time visual systems in applications such as smart camera surveillance, smart environments, and drones necessitates the improvement of methods for visual active monitoring and control. Traditionally, the active monitoring task has been handled through a pipeline of modules such as detection, filtering, and control. However, such methods are difficult to jointly optimize and tune their various parameters for real-time processing in resource constraint systems. In this… Expand


End-to-end Active Object Tracking via Reinforcement Learning
An end-to-end solution via deep reinforcement learning, where a ConvNet-LSTM function approximator is adopted for the direct frame-toaction prediction and an environment augmentation technique and a customized reward function are proposed, which are crucial for a successful training. Expand
End to End Learning for Self-Driving Cars
A convolutional neural network is trained to map raw pixels from a single front-facing camera directly to steering commands and it is argued that this will eventually lead to better performance and smaller systems. Expand
Object Detection With Deep Learning: A Review
This paper provides a review of deep learning-based object detection frameworks and focuses on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further. Expand
Training Deep Neural Networks for Visual Servoing
A deep neural network-based method to perform high-precision, robust and real-time 6 DOF positioning tasks by visual servoing and proposes the training of a scene-agnostic network by feeding in both the desired and current images into a deep network. Expand
On the Interaction Between Deep Detectors and Siamese Trackers in Video Surveillance
By integrating a change detection mechanism into a deep Siamese-FC tracker, its template can be adapted in response to changes in a target's appearance that lead to drifts during tracking, which highlights the importance for reliable VOT of using accurate detectors. Expand
Video Analysis in Pan-Tilt-Zoom Camera Networks
This tutorial presents cooperative localization and tracking methods, i.e., multiagentand consensus-based approaches to jointly compute the target's properties such as ground-plane position and velocity and discusses implementation aspects for these video processing techniques on embedded smart cameras, with a special focus on data access properties. Expand
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
This work proposes a technique for producing ‘visual explanations’ for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent and explainable, and shows that even non-attention based models learn to localize discriminative regions of input image. Expand
Optimizing the Detection Performance of Smart Camera Networks Through a Probabilistic Image-Based Model
A flexible uncertainty model that can be used to characterize the detection behavior in a camera network is introduced and how to utilize the model to formulate detection-aware optimization algorithms that can been used to reconfigure the network in order to improve the overall detection efficiency and thus increase the effective number of detected targets. Expand
Beyond the Static Camera: Issues and Trends in Active Vision
This chapter is dedicated to active vision systems, trying to achieve a trade-off between these two aims and examining the use of high-level reasoning in such scenarios. Expand
Detect to Track and Track to Detect
This paper sets up a ConvNet architecture for simultaneous detection and tracking, using a multi-task objective for frame-based object detection and across-frame track regression, and introduces correlation features that represent object co-occurrences across time to aid the ConvNet during tracking. Expand