Robust AUV Visual Loop-Closure Detection Based on Variational Autoencoder Network

Wang, Yangyang; Ma, Xiaorui; Wang, Jie; Hou, Shilong; Ju, Dai; Gu, Dongbing; Wang, Hongyu

doi:10.1109/tii.2022.3145860

Cited by 18 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A UTONOMOUS underwater vehicles (AUVs) have demonstrated significant potentials in the exploitation and utilization of marine resources in recent years, for instance, deep-sea exploration, subaqueous construction, underwater rescue, routine seafood products monitoring, pipeline detecting and real-time seabed mapping [1], [2], [3], [4]. For complex and dynamic marine environments, self-localization function of AUVs is the foundation for accomplishing potential applications.…”

Section: Introductionmentioning

confidence: 99%

Robust Real-Time AUV Self-Localization Based on Stereo Vision-Inertia

Wang

et al. 2023

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

Autonomous underwater vehicles (AUVs) play an important role in deep-sea exploration, in which AUV selflocalization is a key component. However, due to poor visibility caused by challenging marine environments, AUVs are often equipped with high-cost and heavy-weight acoustic sensors to accomplish localization tasks. We propose a robust real-time AUV self-localization method based on stereo camera and inertial sensor, which merges point and diagonal features, as well as inertial measurements to overcome the challenges of poor visibility. Our method also includes an underwater loop detection algorithm based on the combination of points and diagonal segments, which can extract effective binary descriptors in lowtextured underwater scenarios. Furthermore, we develop an AUV self-localization system based on a real-time, portable, low-cost, and small volume sensor suite. Finally, we test the proposed method in a real underwater environment using our sensor suite, and the experimental results demonstrate the effectiveness of the proposed method under dramatically changing underwater scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

Robust Real-Time AUV Self-Localization Based on Stereo Vision-Inertia

Wang

et al. 2023

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

show abstract

“…Department of forestry in India currently handling more projects related to animal health care using IoT and species care such as Near Real Time Monitoring of Active Fires Using MODIS Based Web Fire Mappers, Monitoring of Forest Cover in Selected Protected Areal, Status of Forest Cover in Tiger Reserves etc. Researchers should plan and pick a suitable framework to solve specific biological concerns, given the range of configuration & functionalities available in modern GPS devices [2]. The impacts of human activities such as hunting of wild creatures and tree trimming, which also pose a major risk to animals, have made wildlife safety a priority in recent years.…”

Section: Introductionmentioning

confidence: 99%

A Novel Approach to Diagnose the Animal Health Continuous Monitoring Using IoT Based Sensory Data

Kandepan¹,

Venkatesan²

2022

I2M

View full text Add to dashboard Cite

Monitoring the health of humans in everyday life is quite challenging. Smart wearables have been increasingly important in recent technologies for monitoring and indicating our current health status, which is utilised to appropriately diagnose our health. Monitoring animals' health raises several concerns. We must wait for veterinary specialists to assess and diagnose whether the animals are suffering only in known regions. The result is delayed treatment and degradation of animal health. Therefore, primary health diagnosis is needed. However, mounting equipment was required to identify these features. This research leads to the recognition of the behaviour of animals through this technique, which facilitates the assessment of the health of animals. The use of Wireless Sensor Networks (WSN) and IoT features an Animals Smart Healthcare Monitoring (ASHM) system for this research to track animal behavior with high precision using sensors and to detect animals' health with great precision. We proposed designing a system that would track the movement and health of an animal. This can be achieved by developing a system with animal smart health monitoring system. The sensor can be mounted on the animal body to get the desired physiological parameters like temperature, heart rate, respiratory rate, ECG, and Blood pressure. This health surveillance system method has reduced the mean latency by 75% and provides results with an output accuracy of 98%.

show abstract

“…1). It has been demonstrated that a CNN classifier that is employed by a standard single-view VPR module [1,2,3] can provide domain-invariant visual cues [11,12,13], such as activations that are invoked by a view image. This motivated us to reformulate the NBV problem to use domain-invariant visual cues instead of a raw view image as the visual input to the NBV planner.…”

Section: Introductionmentioning

confidence: 99%

Active Domain-Invariant Self-Localization Using Ego-Centric and World-Centric Maps

Kurauchi¹,

Yamamoto²,

Yoshida³

2022

Preprint

View full text Add to dashboard Cite

The training of a next-best-view (NBV) planner for visual place recognition (VPR) is a fundamentally important task in autonomous robot navigation, for which a typical approach is the use of visual experiences that are collected in the target domain as training data. However, the collection of a wide variety of visual experiences in everyday navigation is costly and prohibitive for real-time robotic applications. We address this issue by employing a novel domain-invariant NBV planner. A standard VPR subsystem based on a convolutional neural network (CNN) is assumed to be available, and its domain-invariant state recognition ability is proposed to be transferred to train the domain-invariant NBV planner. Specifically, we divide the visual cues that are available from the CNN model into two types: the output layer cue (OLC) and intermediate layer cue (ILC). The OLC is available at the output layer of the CNN model and aims to estimate the state of the robot (e.g., the robot viewpoint) with respect to the world-centric view coordinate system. The ILC is available within the middle layers of the CNN model as a high-level description of the visual content (e.g., a saliency image) with respect to the ego-centric view. In our framework, the ILC and OLC are mapped to a state vector and subsequently used to train a multiview NBV planner via deep reinforcement learning. Experiments using the public NCLT dataset validate the effectiveness of the proposed method.

show abstract

Robust AUV Visual Loop-Closure Detection Based on Variational Autoencoder Network

Cited by 18 publications

References 31 publications

Robust Real-Time AUV Self-Localization Based on Stereo Vision-Inertia

Robust Real-Time AUV Self-Localization Based on Stereo Vision-Inertia

A Novel Approach to Diagnose the Animal Health Continuous Monitoring Using IoT Based Sensory Data

Active Domain-Invariant Self-Localization Using Ego-Centric and World-Centric Maps

Contact Info

Product

Resources

About