SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.17242 · CVPR · 2021

Dogfight: Detecting Drones from Drones Videos

Mubarak Shah, Waqas Sultani, Muhammad Ashraf

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

As airborne vehicles are becoming more autonomous and ubiquitous, it has become vital to develop the capability to detect the objects in their surroundings. This paper attempts to address the problem of drones detection from other flying drones. The erratic movement of the source and target drones, small size, arbitrary shape, large intensity variations, and occlusion make this problem quite challenging. In this scenario, region-proposal based methods are not able to capture sufficient discriminative foregroundbackground information. Also, due to the extremely small size and complex motion of the source and target drones, feature aggregation based methods are unable to perform well. To handle this, instead of using region-proposal based methods, we propose to use a two-stage segmentation-based approach employing spatio-temporal attention cues. During the first stage, given the overlapping frame regions, detailed contextual information is captured over convolution feature maps using pyramid pooling. After that pixel and channel-wise attention is enforced on the feature maps to ensure accurate drone localization. In the second stage, first stage detections are verified and new probable drone locations are explored. To discover new drone locations, motion boundaries are used. This is followed by tracking candidate drone detections for a few frames, cuboid formation, extraction of the 3D convolution feature map, and drones detection within each cuboid. The proposed approach is evaluated on two publicly available drone detection datasets and outperforms several competitive baselines.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2103.17242")
get_code_for_paper("2103.17242")
have("2103.17242")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2103.17242.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2103.17242.svg)](https://syntology.ai/paper/2103.17242)

Connect an agent — have() is free.