Pedestrian detection is a specific instance of the more general problem of object detection in computer vision. A balance between detection accuracy and speed is a desirable trait for pedestrian detection systems in many applications such as self-driving cars. In this paper, we follow the wisdom of " and less is often more" to achieve this balance. We propose a lightweight mechanism based on semantic segmentation to reduce the number of anchors to be processed. We furthermore unify this selection with the intra-anchor feature pooling strategy adopted in high performance two-stage detectors such as Faster-RCNN. Such a strategy is avoided in one-stage detectors like SSD in favour of faster inference but at the cost of reducing the accuracy vis-à-vis two-stage detectors. However our anchor selection renders it practical to use feature pooling without giving up the inference speed.Our proposed approach succeeds in detecting pedestrians with state-of-art performance on caltech-reasonable and ciypersons datasets with inference speeds of ∼ 32 fps.
Fragmentation is one of the major issues in elastic optical network (EON) due to its dynamic characteristics which may possibly degrade the spectrum efficiency. Several techniques have been presented in the literature to get the optimal solution of this problem while multi-path provisioning comes out to be very compelling among them. In multi-path provisioning enable networks, multi-path routing and spectrum assignment (MPRSA) creates further complications due to the hardware availability and more spectrum consumption. This paper presents a novel technique termed as adaptive service provisioning (ASP) to come up with a solution of the MPRSA problem and it minimizes the spectrum fragments in the network by precisely managing the scattered spectrum slots. This technique performs the adaptive traffic demand splitting on disjoint paths in case it is unable to be served by k-shortest routing paths based on the parameters such as hardware support, capacity available and demand. An integer linear programming (ILP) model as well as a heuristic algorithm for solving MPRSA problem in large optical networks where ILP is not compliant is developed. Numerical simulations are performed to investigate the performance of the algorithm in terms of blocking probability and spectrum utilization.
Elastic optical networks (EONs) are a promising technology for the next-generation optical network, and advanced reservation (AR) applications have been growing expeditiously over the past few years. Thus, the routing and spectrum allocation problem for AR requests has become a significant concern. This paper proposes an approach named outright fit advanced resource reservation to improve the spectral resource allocation efficiency for AR connection requests. Our proposed approach works in two stages: The proposed resource reservation strategy first uses an outright fit resource allocation strategy to reserve the spectral resource for a connection request within the absolute best service window and leaves adequate spectral resources for subsequent requests. If a connection request cannot get resources in the first stage, the proposed optimal rescheduling technique then is applied to serve the request. Our proposed optimal rescheduling technique uses spectrum shifting and reallocation without altering the routing paths, and its optimal characteristic decreases the number of rescheduling operations, thereby decreasing the rescheduling computational complexity and cost, which improves the network’s quality of service. Moreover, this rescheduling approach increases the opportunities for successful rescheduling of the requests without inducing many spectrum fragments, significantly reducing the blocking probability. The simulation results illustrate that the proposed approach can considerably enhance the blocking performance and obtains high spectrum utilization.
In this paper, we compute the optimal slot width which provides a good trade-off between the blocking probability and network cost to attain spectral and cost-efficient solution for the next generation optical networks. Here we have determined the blocking performance by varying the slot width from 50 GHz down to 1.5625 GHz followed by the estimation of the network cost by taking into account various network elements viz., transponder, node equipment’s (OXC, SSS, splitter/combiner) and optical amplifiers. Further, an evaluation of the trade-off between blocking performance and network cost is carried out to get the optimal slot width.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.