Video stabilization for an aerial surveillance system using sift and surf

Kaur, Jagdeep; Bathla, Ashok Kumar

doi:10.1109/ngct.2016.7877509

Cited by 5 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each of the above contributions is discussed in detail in the following chapters. Keypoints detection is an important research topic in computer vision with a wide range of applications in human-computer interaction [29], Augmented Reality (AR) and Virtual Reality (VR) [30], gaming and filmmaking [31], and security and surveillance [32]. Various machine learning techniques with carefully engineered feature extractors have been developed to make precise predictions of different keypoints of interest [33,34].…”

Section: Robot Arm Manipulationmentioning

confidence: 99%

Autonomous Cricothyroid Membrane Detection and Manipulation Using Neural Networks and a Robot Arm for First-Aid Airway Management

Han

Ren

et al. 2023

Journal of Medical Devices

View full text Add to dashboard Cite

Cricothyrotomy serves as one of the most efficient surgical interventions when a patient is enduring a Can't Intubate Can't Oxygenate (CICO) scenario. However, medical background and professional training are required for the provider to establish a patent airway successfully. Motivated by robotics applications in search and rescue, this work focuses on applying artificial intelligence techniques on the precise localization of the incision site, the cricothyroid membrane (CTM), of the injured using an RGB-D camera, and the manipulation of a robot arm with reinforcement learning to reach the detected CTM keypoint. In this paper, we further improved the success rate of our previously proposed Hybrid Neural Network (HNNet) in detecting the CTM from 84.3% to 96.6%, yielding an error of less than 5mm in real-world coordinates. In addition, a separate neural network was trained to manipulate a robotic arm for reaching a waypoint with an error of less than 5mm. An integrated system that combines both the perception and the control techniques was built and experimentally validated using a human-size manikin to validate the overall concept of autonomous cricothyrotomy with an RGB-D camera and a robotic manipulator using artificial intelligence.

show abstract

Section: Robot Arm Manipulationmentioning

confidence: 99%

Autonomous Cricothyroid Membrane Detection and Manipulation Using Neural Networks and a Robot Arm for First-Aid Airway Management

Han

Ren

et al. 2023

Journal of Medical Devices

View full text Add to dashboard Cite

show abstract

“…Jagdeep Kaur et.al [18] has proposed video stabilization and moving objects detection module. SIFT and SURF are used as descriptors.…”

Section: Related Workmentioning

confidence: 99%

Obstacle avoidance and distance measurement for unmanned aerial vehicles using monocular vision

Aswini

Uma

2019

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Unmanned Aerial Vehicles or commonly known as drones are better suited for "dull, dirty, or dangerous" missions than manned aircraft. The drone can be either remotely controlled or it can travel as per predefined path using complex automation algorithm built during its development. In general, Unmanned Aerial Vehicle (UAV) is the combination of Drone in the air and control system on the ground. Design of an UAV means integrating hardware, software, sensors, actuators, communication systems and payloads into a single unit for the application involved. To make it completely autonomous, the most challenging problem faced by UAVs is obstacle avoidance. In this paper, a novel method to detect frontal obstacles using monocular camera is proposed. Computer Vision algorithms like Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Feature (SURF) are used to detect frontal obstacles and then distance of the obstacle from camera is calculated. To meet the defined objectives, designed system is tested with self-developed videos which are captured by DJI Phantom 4 pro.</span>

show abstract

“…This is known to be computationally intensive and time consuming [1,2,3,4]. Even if the camera shake were accurately known (through orientation sensors inside camera or by other means), the frame by frame correction of the shake would be a computationally intensive task [5,6].…”

Section: Introductionmentioning

confidence: 99%

Applying Approximate Computing Principles for Real-Time Rolling Shake Hyper-Stabilization During Video Recording

Singh

Ansari

2022

SSRN Journal

View full text Add to dashboard Cite

Video stabilization for an aerial surveillance system using sift and surf

Cited by 5 publications

References 14 publications

Autonomous Cricothyroid Membrane Detection and Manipulation Using Neural Networks and a Robot Arm for First-Aid Airway Management

Autonomous Cricothyroid Membrane Detection and Manipulation Using Neural Networks and a Robot Arm for First-Aid Airway Management

Obstacle avoidance and distance measurement for unmanned aerial vehicles using monocular vision

Applying Approximate Computing Principles for Real-Time Rolling Shake Hyper-Stabilization During Video Recording

Contact Info

Product

Resources

About