SummaryAn Adhoc network is a combination of mobile nodes that works without centralized infrastructure. Every mobile node acts as host and routers. Furthermore, it also forward packets to other mobile nodes in network which are not within the direct transmission range. Mobile Ad hoc networks are easily exposed to various network layer attacks that include black hole, wormhole, and DOS attack. Wormhole attack is one among the severe attacks in MANET. Wormhole attacker receives the packets at any particular location in the network and disturbs the flow of packet by tunneling them to another location. In this paper, advanced mechanism is presented against these wormhole attacks in a MANET. Existing methods use Quality of Service (QoS) for entire network to detect attacks. Our method makes use of the packet delivery ratio and round trip time for each node, and it also detects active and passive attacks. Thus, the complete identification of wormhole attack is possible using the proposed method.

No abstract

No abstract

Typically a 1-2MP CCTV camera generates around 7-12GB of data per day. Frame-by-frame processing of such an enormous amount of data requires hefty computational resources. In recent years, compressive sensing approaches have shown impressive compression results by reducing the sampling bandwidth. Different sampling mechanisms were developed to incorporate compressive sensing in image and video acquisition. Though all-CMOS [1, 2] sensor cameras that perform compressive sensing can help save a lot of bandwidth on sampling and minimize the memory required to store videos, the traditional signal processing, and deep learning models can realize operations only on the reconstructed data. To realize the original uncompressed domain, most reconstruction techniques are computationally expensive and time-consuming. To bridge this gap, we propose a novel task of detection and localization of objects directly on the compressed frames. Thereby mitigating the need to reconstruct the frames and reducing the search rate up to 20× (compression rate). We achieved an accuracy of 46.27% mAP with the proposed model on a GeForce GTX 1080 Ti. We were also able to show real-time inference on an NVIDIA TX2 embedded board with 45.11% mAP, thereby achieving the best balance between the accuracy, inference time, and memory constraints.

No abstract