Search Results

• Develop a deep learning based object detector on radar and camera data fusion.
• Employ YOLOv8 object detector for radar and camera target detection individually.
• Apply Adam optimizer with BiLSTM model to classify detected objects.

Object detection, the process of detecting and classifying objects within a given environment, forms the foundational element. Multisensory fusion incorporates data from diverse sensors, like radar and cameras, to refine the reliability and ...

Human activity depends on the oceans for food, transportation, leisure, and many more purposes. Oceans cover 70% of the Earth’s surface, but most of them are unknown to humankind. This is the reason why underwater imaging is a valuable resource ...

• We present an object detection pipeline for Marine Science based on the Compute Continuum paradigm.
• The Object detector has been trained for Mediterranean fishes, while related works normally consider tropical fishes.
• The pipeline ...

The continuous development of optical remote sensing images has provided a valuable data source for object detection samples. Labelling these samples for deep learning research in optical remote sensing is crucial yet time-consuming. Traditional ...

Inspired by the ambitions envisioned in the Fourth Industrial Revolution for aquaculture, also known as Aquaculture 4.0, the aquaculture (marine animal farming) industry is seeking to adopt data-driven Artificial Intelligence (AI) to help ...

• Novel AI-system to enhance animal detection accuracy in high-density areas.
• Enhanced DBScan algorithm for time series for density-based spatial clustering.
• AI model with robustness in handling occlusion, turbidity, and overlapping.

Fast and accurate object detection in foggy weather is crucial for visual tasks such as autonomous driving and video surveillance. Existing methods typically preprocess images with enhancement techniques before the object detector, so that the ...

• We design a Restoration Subnetwork Module (RSM) based on the atmospheric scattering model and three Adaptive Feature Fusion Modules (AFFM) for encouraging the network to learn more discriminative features from foggy images.
• We ...

Lightweight network design is crucial for optimizing speed and accuracy in computer vision tasks on mobile platforms with limited resources. Widely adopted models, such as EfficientNet and RegNet have achieved significant success by integrating ...

• We propose a novel CFG block that effectively utilizes the feature redundancy before and after the PWConv without any accompanying activation function. And we introduce a more efficient attention mechanism, the CCA block, which is ...

Side-scan sonar small target detection becomes fundamental work for side-scan sonar applications which holds vital importance for marine engineering, maritime military, and so on. However, existing algorithms suffer from performance degradation ...

• Improving the detection performance of side-scan sonar by fusing useful features in a continuous sequence.
• Sonar data is considered for the first time as a combination of continuous time series and the corresponding dataset is created.

• Integrating a novel semantic segmentation branch into the YOLOv8 network.
• Proposing a multi-task learning network YOLO-FD for detection and segmentation.
• Weight uncertainty and PCGrad are employed to YOLO-FD.
• Achieving accurate ...

Fish diseases often exhibit high risks of contagion, resulting in substantial economic losses. Accurate assessment of fish disease severity during diagnosis using deep learning poses a considerable challenge. Currently, deep learning models ...

Sonar imaging is an underwater detection technology that relies on the transmission and reception of acoustic pulse waves. This technique plays a crucial role in various domains including underwater archaeology, energy exploration, and ...

Several deep learning algorithms are currently focused on object detection in adverse weather scenarios for autonomous driving systems. However, these algorithms face challenges in real-time scenarios, leading to a reduction in detection ...

Few-shot object detection (FSOD) aims at learning a novel class object detector with abundant base class samples and a limited number of novel class samples. Some recent methods assume that base class images contain unlabeled novel class ...

Open-vocabulary object detection aims to train a detector capable of recognizing various novel classes. Most existing studies exploit image-level weak supervision to generate pseudo object boxes for novel class training. However, the generated ...

• Open-vocabulary object detection without using box-annotated images of novel classes.
• Better exploitation of image-level weak supervision for novel class training.
• Proposed debiased curriculum self-training for accurate pseudo-...

Autonomous vehicles (AV) are anticipated to have a significant positive impact on society by reducing accidents and optimizing traffic. However, they are primarily based on improvements in various artificial intelligence (AI) methods and ...

In this survey, we provide a comprehensive study on the assistive technological devices which help visually impaired persons in their day-to-day lives. With various forms of disabilities such as visual, auditory, mobility, or cognitive impairment ...

Aiming at the limitations of visible images in object detection, this paper proposes a dual-branch network object detection algorithm based on dual-modality fusion of visible and infrared images. Based on YOLOv7-s, the algorithm firstly introduces ...

The prevailing models for object detection are often beset by a dearth of generalizability across domains. Specifically, while these models may perform exceptionally well on a given dataset, their efficacy can plummet when confronted with novel ...$$$$$$

With the construction of intelligent grids, unmanned aerial vehicle have been widely employed to inspect transmission lines. The inspection process generates a large amount of data, which requires a lightweight model to reduce computational ...

Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific datasets, ...

• Language-aware Framework for Object Detection.
• Multi-datasets Joint Training.
• Detection Pretraining.

Oracle bone characters (OBCs) are ancient ideographs for divination and memorization, as well as first-hand evidence of ancient Chinese culture. The detection of OBC is the premise of advanced studies and was mainly done by authoritative experts ...

• A semi-supervised framework called OBCTeacher is proposed for OBC detection.
• A geometric-priori assignment and a heatmap polishing procedure are introduced.
• A class information re-weighting module and a contrastive anchor loss are ...

Conveyor belt can enhance transportation efficiency and reduce labor intensity, which is extensively applied in material transportation. However, the deviation of conveyor belt commonly leads to malfunctions in the transmission system, affecting ...

• A conveyor belt deviation discrimination method CDSwD is proposed.
• The roller information and the conveyor belt contour information are combined.
• The proposed method can avoid the effect of camera position deviation.
• ER-YOLOv5 ...