Alert button
Picture for Sahan Liyanaarachchi

Sahan Liyanaarachchi

Alert button

The Role of Early Sampling in Age of Information Minimization in the Presence of ACK Delays

Aug 15, 2023
Sahan Liyanaarachchi, Sennur Ulukus

Figure 1 for The Role of Early Sampling in Age of Information Minimization in the Presence of ACK Delays
Figure 2 for The Role of Early Sampling in Age of Information Minimization in the Presence of ACK Delays
Figure 3 for The Role of Early Sampling in Age of Information Minimization in the Presence of ACK Delays
Figure 4 for The Role of Early Sampling in Age of Information Minimization in the Presence of ACK Delays

We study the structure of the optimal sampling policy to minimize the average age of information when the channel state (i.e., busy or idle) is not immediately perceived by the transmitter upon the delivery of a sample due to random delays in the feedback (ACK) channel. In this setting, we show that it is not always optimal to wait for ACKs before sampling, and thus, early sampling before the arrival of an ACK may be optimal. We show that, under certain conditions on the distribution of the ACK delays, the optimal policy is a mixture of two threshold policies.

Viaarxiv icon

Extending Multi-Object Tracking systems to better exploit appearance and 3D information

Dec 25, 2019
Kanchana Ranasinghe, Sahan Liyanaarachchi, Harsha Ranasinghe, Mayuka Jayawardhana

Figure 1 for Extending Multi-Object Tracking systems to better exploit appearance and 3D information
Figure 2 for Extending Multi-Object Tracking systems to better exploit appearance and 3D information
Figure 3 for Extending Multi-Object Tracking systems to better exploit appearance and 3D information
Figure 4 for Extending Multi-Object Tracking systems to better exploit appearance and 3D information

Tracking multiple objects in real time is essential for a variety of real-world applications, with self-driving industry being at the foremost. This work involves exploiting temporally varying appearance and motion information for tracking. Siamese networks have recently become highly successful at appearance based single object tracking and Recurrent Neural Networks have started dominating both motion and appearance based tracking. Our work focuses on combining Siamese networks and RNNs to exploit appearance and motion information respectively to build a joint system capable of real time multi-object tracking. We further explore heuristics based constraints for tracking in the Birds Eye View Space for efficiently exploiting 3D information as a constrained optimization problem for track prediction.

* 7 pages 
Viaarxiv icon

Bipartite Conditional Random Fields for Panoptic Segmentation

Dec 11, 2019
Sadeep Jayasumana, Kanchana Ranasinghe, Mayuka Jayawardhana, Sahan Liyanaarachchi, Harsha Ranasinghe

Figure 1 for Bipartite Conditional Random Fields for Panoptic Segmentation
Figure 2 for Bipartite Conditional Random Fields for Panoptic Segmentation
Figure 3 for Bipartite Conditional Random Fields for Panoptic Segmentation
Figure 4 for Bipartite Conditional Random Fields for Panoptic Segmentation

We tackle the panoptic segmentation problem with a conditional random field (CRF) model. Panoptic segmentation involves assigning a semantic label and an instance label to each pixel of a given image. At each pixel, the semantic label and the instance label should be compatible. Furthermore, a good panoptic segmentation should have a number of other desirable properties such as the spatial and color consistency of the labeling (similar looking neighboring pixels should have the same semantic label and the instance label). To tackle this problem, we propose a CRF model, named Bipartite CRF or BCRF, with two types of random variables for semantic and instance labels. In this formulation, various energies are defined within and across the two types of random variables to encourage a consistent panoptic segmentation. We propose a mean-field-based efficient inference algorithm for solving the CRF and empirically show its convergence properties. This algorithm is fully differentiable, and therefore, BCRF inference can be included as a trainable module in a deep network. In the experimental evaluation, we quantitatively and qualitatively show that the BCRF yields superior panoptic segmentation results in practice.

Viaarxiv icon