Network For Object Recognition Research Articles

R-PointNet: Robust 3D Object Recognition Network for Real-World Point Clouds Corruption

Point clouds obtained with 3D scanners in realistic scenes inevitably contain corruption, including noise and outliers. Traditional algorithms for cleaning point cloud corruption require the selection of appropriate parameters based on the characteristics of the scene, data, and algorithm, which means that their performance is highly dependent on the experience and adaptation of the algorithm itself to the application. Three-dimensional object recognition networks for real-world recognition tasks can take the raw point cloud as input and output the recognition results directly. Current 3D object recognition networks generally acquire uniform sampling points by farthest point sampling (FPS) to extract features. However, sampled defective points from FPS lower the recognition accuracy by affecting the aggregated global feature. To deal with this issue, we design a compensation module, named offset-adjustment (OA). It can adaptively adjust the coordinates of sampled defective points based on neighbors and improve local feature extraction to enhance network robustness. Furthermore, we employ the OA module to build an end-to-end network based on PointNet++ framework for robust point cloud recognition, named R-PointNet. Experiments show that R-PointNet reaches state-of-the-art performance by 92.5% of recognition accuracy on ModelNet40, and significantly outperforms previous networks by 3–7.7% on the corruption dataset ModelNet40-C for robustness benchmark.

Multi-scale aware turbulence network for underwater object recognition

Underwater imagery is subject to distortion, and the presence of turbulence in the fluid medium poses difficulties in accurately discerning objects. To tackle these challenges pertaining to feature extraction, this research paper presents a novel approach called the multi-scale aware turbulence network (MATNet) method for underwater object identification. More specifically, the paper introduces a module known as the multi-scale feature extraction pyramid network module, which incorporates dense linking strategies and position learning strategies to preprocess object contour features and texture features. This module facilitates the efficient extraction of multi-scale features, thereby enhancing the effectiveness of the identification process. Following that, the extracted features undergo refinement through comparison with positive and negative samples. Ultimately, the study introduces multi-scale object recognition techniques and establishes a multi-scale object recognition network for the precise identification of underwater objects, utilizing the enhanced multi-scale features. This process entails rectifying the distorted image and subsequently recognizing the rectified object. Extensive experiments conducted on an underwater distorted image enhancement dataset demonstrate that the proposed method surpasses state-of-the-art approaches in both qualitative and quantitative evaluations.

Implementation of Image Recognition for Human detection in Underwater Images

Recent advances in deep learning have resolved the challenges of detection of objects underwater. Specialized methods have been developed as a result of the particular characteristics of small, fuzzy objects and heterogeneous noise. The Sample-Weighted Network (SWIPE Net) for small object recognition is one of them, as are frameworks with feature enhancement and anchor refining. Additionally, upgraded versions of the attention processes and YOLOv7 have been released. These advancements help with tracking the effects of clean energy technologies, developing accurate and reliable underwater object detection systems, bridging the communication gap between the deaf and hearing-impaired, and automating the analysis of underwater imagery for the extraction of ecological data.

Transformer-Based Feature Compensation Network for Aerial Photography Person and Ground Object Recognition

Visible-infrared person re-identification (VI-ReID) aims at matching pedestrian images with the same identity between different modalities. Existing methods ignore the problems of detailed information loss and the difficulty in capturing global features during the feature extraction process. To solve these issues, we propose a Transformer-based Feature Compensation Network (TFCNet). Firstly, we design a Hierarchical Feature Aggregation (HFA) module, which recursively aggregates the hierarchical features to help the model preserve detailed information. Secondly, we design the Global Feature Compensation (GFC) module, which exploits Transformer’s ability to capture long-range dependencies in sequences to extract global features. Extensive results show that the rank-1/mAP of our method on the SYSU-MM01 and RegDB datasets reaches 60.87%/58.87% and 91.02%/75.06%, respectively, which is better than most existing excellent methods. Meanwhile, to demonstrate our method‘s transferability, we also conduct related experiments on two aerial photography datasets.

Research on Convolution Neural Network for Object Detection and Recognition

The state-of-the-art object detection networks for natural images have recently demonstrated impressive performances. However, the complexity of object’s shape and orientation exposes the limited capacity of these networks for strip-like rotated assembled object detection which are common in any dataset as well as real im- ages. In this project, I embrace this observation and introduce the Faster Rotated Region-based Convolutional Neural Network (Faster RR-CNN), which can learn and accurately extract features of rotated regions and arbitrary-oriented objects precisely. In comparison with the classic Faster RCNN, Faster RR-CNN has three important new components including a skew non-maximum suppression, a rotated bounding box regression model and a rotated region of interest (RRoI) pooling layer. I conduct experiments using the PASCAL VOC 2012 dataset, demonstrat-ing the potential ability of this novel network in detecting oriented objects.

LVNet: A lightweight volumetric convolutional neural network for real-time and high-performance recognition of 3D objects

LVNet: A lightweight volumetric convolutional neural network for real-time and high-performance recognition of 3D objects

G2T-SNN: Fusing Topological Graph and Gaussian Prior Spiking Neural Networks for Tactile Object Recognition

G2T-SNN: Fusing Topological Graph and Gaussian Prior Spiking Neural Networks for Tactile Object Recognition

UNet Based on Multi-Object Segmentation and Convolution Neural Network for Object Recognition

UNet Based on Multi-Object Segmentation and Convolution Neural Network for Object Recognition

TransCNNLoc: End-to-end pixel-level learning for 2D-to-3D pose estimation in dynamic indoor scenes

Accurate localization in GPS-denied environments has always been a core issue in computer vision and robotics research. In indoor environments, vision-based localization methods are susceptible to changes in lighting conditions, viewing angles, and environmental factors, resulting in localization failures or limited generalization capabilities. In this paper, we propose the TransCNNLoc framework, which consists of an encoding–decoding network designed to learn more robust image features for camera pose estimation. In the image feature encoding stage, CNN and Swin Transformer are integrated to construct the image feature encoding module, enabling the network to fully extract global context and local features from images. In the decoding stage, multi-level image features are decoded through cross-layer connections while computing per-pixel feature weight maps. To enhance the framework’s robustness to dynamic objects, a dynamic object recognition network is introduced to optimize the feature weights. Finally, a multi-level iterative optimization from coarse to fine levels is performed to recover six degrees of freedom camera pose. Experiments were conducted on the publicly available 7scenes dataset as well as a dataset collected under changing lighting conditions and dynamic scenes for accuracy validation and analysis. The experimental results demonstrate that the proposed TransCNNLoc framework exhibits superior adaptability to dynamic scenes and lighting changes. In the context of static environments within publicly available datasets, the localization technique introduced in this study attains a maximal precision of up to 5 centimeters, consistently achieving superior outcomes across a majority of the scenarios. Under the conditions of dynamic scenes and fluctuating illumination, this approach demonstrates an enhanced precision capability, reaching up to 3 centimeters. This represents a substantial refinement from the decimeter scale to a centimeter scale in precision, marking a significant advancement over the existing state-of-the-art (SOTA) algorithms. The open-source repository for the method proposed in this paper can be found at the following URL: github.com/Geelooo/TransCNNloc.

Cross-Level Multi-Modal Features Learning With Transformer for RGB-D Object Recognition

Object recognition, one of the main goals of robot vision, is a vital prerequisite for service robots to perform domestic tasks. Thanks to the rich sense of information provided by RGB-D sensors, RGB-D-based object recognition has received increasing attention. However, the existing works focus on collaborative RGB and depth data for object recognition, while ignoring the influence of depth image quality on recognition performance. Moreover, in real-world scenarios, there are many objects with strong similarity from certain observation angles, which poses a challenge for the service robot to recognize objects accurately. In this paper, we propose CNN-TransNet, a novel end-to-end Transformer-based architecture with convolutional neural networks (CNNs) for RGB-D object recognition. In order to deal with the effect of high inter-class similarity, discriminative multi-modal feature representations are generated by learning and relating multi-modal features at multiple levels. Besides, we employ a multi-modal fusion and projection (MMFP) module to reweight the contribution of each modality to address the problem of poor-quality depth image. Our proposed approach achieves state-of-the-art performance on three datasets (including Washington RGB-D Object Dataset, JHUIT-50, and Object Clutter Indoor Dataset), with accuracy of 95.4%, 98.1%, and 94.7%, respectively. The results demonstrate the effectiveness and superiority of the proposed model in RGB-D object recognition task.

A “Hardware-Friendly” Foreign Object Identification Method for Belt Conveyors Based on Improved YOLOv8

As a crucial element in coal transportation, conveyor belts play a vital role, and monitoring their health is essential for the coal mine transportation system’s safe and efficient operation. This paper introduces a new ‘hardware-friendly’ method for monitoring belt conveyor damage, aiming to address the issue of large parameters and computational requirements in existing deep learning-based foreign object detection methods and their challenges in deploying on edge devices with limited computing power. This method is tailored towards edge computing and aims to reduce the parameters and computational load of foreign object recognition networks deployed on edge computing devices. This method improves the YOLOv8 object detection network and redesigns a novel lightweight ShuffleNetV2 network as the backbone network, making the network more delicate in recognizing foreign object features while reducing redundant parameters. Additionally, a simple parameter-free attention mechanism called SimAM is introduced to further enhance recognition efficiency without imposing additional computational burden. Experimental results demonstrate that the improved foreign object recognition method achieves a detection accuracy of 95.6% with only 1.6 M parameters and 4.7 G model computational load (FLOPs). Compared to the baseline YOLOv8n, the detection accuracy has improved by 3.3 percentage points, while the number of parameters and model computational load have been reduced by 48.4% and 42.0%, respectively. These works are more friendly to edge computing devices that tend to “hardware friendly” algorithms. The improved algorithm can reduce latency in the data transmission process, enabling the accurate and timely detection of non-coal foreign objects on the conveyor belt. This provides assurance for the subsequent host computer system to promptly identify and address foreign objects, thereby ensuring the safety and efficiency of the belt conveyor.

InOR-Net: Incremental 3-D Object Recognition Network for Point Cloud Representation.

3-D object recognition has successfully become an appealing research topic in the real world. However, most existing recognition models unreasonably assume that the categories of 3-D objects cannot change over time in the real world. This unrealistic assumption may result in significant performance degradation for them to learn new classes of 3-D objects consecutively due to the catastrophic forgetting on old learned classes. Moreover, they cannot explore which 3-D geometric characteristics are essential to alleviate the catastrophic forgetting on old classes of 3-D objects. To tackle the above challenges, we develop a novel Incremental 3-D Object Recognition Network (i.e., InOR-Net), which could recognize new classes of 3-D objects continuously by overcoming the catastrophic forgetting on old classes. Specifically, category-guided geometric reasoning is proposed to reason local geometric structures with distinctive 3-D characteristics of each class by leveraging intrinsic category information. We then propose a novel critic-induced geometric attention mechanism to distinguish which 3-D geometric characteristics within each class are beneficial to overcome the catastrophic forgetting on old classes of 3-D objects while preventing the negative influence of useless 3-D characteristics. In addition, a dual adaptive fairness compensations' strategy is designed to overcome the forgetting brought by class imbalance by compensating biased weights and predictions of the classifier. Comparison experiments verify the state-of-the-art performance of the proposed InOR-Net model on several public point cloud datasets.

Machine learning-ready remote sensing data for Maya archaeology

In our study, we set out to collect a multimodal annotated dataset for remote sensing of Maya archaeology, that is suitable for deep learning. The dataset covers the area around Chactún, one of the largest ancient Maya urban centres in the central Yucatán Peninsula. The dataset includes five types of data records: raster visualisations and canopy height model from airborne laser scanning (ALS) data, Sentinel-1 and Sentinel-2 satellite data, and manual data annotations. The manual annotations (used as binary masks) represent three different types of ancient Maya structures (class labels: buildings, platforms, and aguadas – artificial reservoirs) within the study area, their exact locations, and boundaries. The dataset is ready for use with machine learning, including convolutional neural networks (CNNs) for object recognition, object localization (detection), and semantic segmentation. We would like to provide this dataset to help more research teams develop their own computer vision models for investigations of Maya archaeology or improve existing ones.

Direct training high-performance spiking neural networks for object recognition and detection.

The spiking neural network (SNN) is a bionic model that is energy-efficient when implemented on neuromorphic hardwares. The non-differentiability of the spiking signals and the complicated neural dynamics make direct training of high-performance SNNs a great challenge. There are numerous crucial issues to explore for the deployment of direct training SNNs, such as gradient vanishing and explosion, spiking signal decoding, and applications in upstream tasks. To address gradient vanishing, we introduce a binary selection gate into the basic residual block and propose spiking gate (SG) ResNet to implement residual learning in SNNs. We propose two appropriate representations of the gate signal and verify that SG ResNet can overcome gradient vanishing or explosion by analyzing the gradient backpropagation. For the spiking signal decoding, a better decoding scheme than rate coding is achieved by our attention spike decoder (ASD), which dynamically assigns weights to spiking signals along the temporal, channel, and spatial dimensions. The SG ResNet and ASD modules are evaluated on multiple object recognition datasets, including the static ImageNet, CIFAR-100, CIFAR-10, and neuromorphic DVS-CIFAR10 datasets. Superior accuracy is demonstrated with a tiny simulation time step of four, specifically 94.52% top-1 accuracy on CIFAR-10 and 75.64% top-1 accuracy on CIFAR-100. Spiking RetinaNet is proposed using SG ResNet as the backbone and ASD module for information decoding as the first direct-training hybrid SNN-ANN detector for RGB images. Spiking RetinaNet with a SG ResNet34 backbone achieves an mAP of 0.296 on the object detection dataset MSCOCO.

Complementary spatial transformer network for real-time 3D object recognition

Complementary spatial transformer network for real-time 3D object recognition

Leveraging Hand-Object Interactions in Assistive Egocentric Vision.

Egocentric vision holds great promise for increasing access to visual information and improving the quality of life for blind people. While we strive to improve recognition performance, it remains difficult to identify which object is of interest to the user; the object may not even be included in the frame due to challenges in camera aiming without visual feedback. Also, gaze information, commonly used to infer the area of interest in egocentric vision, is often not dependable. However, blind users tend to include their hand either interacting with the object they wish to recognize or simply placing it in proximity for better camera aiming. We propose a method that leverages the hand as the contextual information for recognizing an object of interest. In our method, the output of a pre-trained hand segmentation model is infused to later convolutional layers of our object recognition network with separate output layers for localization and classification. Using egocentric datasets from sighted and blind individuals, we show that the hand-priming achieves more accurate localization than other approaches that encode hand information. Given only object centers along with labels, our method achieves comparable classification performance to the state-of-the-art method that uses bounding boxes with labels.

SOLARNet: A single stage regression based framework for efficient and robust object recognition in aerial images

Object recognition and localization play a crucial role in aerial images and their applications. The aerial images are challenging due to the large aspect ratio, arbitrary orientation, variation in scales, and non-uniform and cluttered object distribution. To address these challenges, we propose an efficient and robust model called the Simultaneous Object Localization and Recognition Network (SOLARNet), which is a fusion network that integrates two different sub-networks: PixelAttentionDetector (PD) and RotationDetector (RD). The PD considers features from different scales and cluttered objects, while RD handles rotation invariance, giving horizontal and oriented object detection results. The state-of-the-art model fails to improve accuracy when images are adversarially attacked. SOLARNet is not only efficient in terms of accuracy but also robust concerning to Fast Gradient Sign Method (FGSM), Basic Iterative Method (BIM), Jacobian Based Saliency Map (JSM) adversarial attacks, which is the crucial factor for any mission-critical system. We have performed experiments and achieved the accuracy on the publicly available DOTA dataset (75.00% mAP, 66.40% mAP) and DIOR dataset (88.60% mAP, 81.50% mAP) for horizontal and oriented object recognition tasks respectively while having high inference speed. Qualitative and quantitative results reported in this paper substantiate the superiority of SOLARNet over other state-of-the-art methodologies.

Accurate online training of dynamical spiking neural networks through Forward Propagation Through Time

With recent advances in learning algorithms, recurrent networks of spiking neurons are achieving performance that is competitive with vanilla recurrent neural networks. However, these algorithms are limited to small networks of simple spiking neurons and modest-length temporal sequences, as they impose high memory requirements, have difficulty training complex neuron models and are incompatible with online learning. Here, we show how the recently developed Forward-Propagation Through Time (FPTT) learning combined with novel liquid time-constant spiking neurons resolves these limitations. Applying FPTT to networks of such complex spiking neurons, we demonstrate online learning of exceedingly long sequences while outperforming current online methods and approaching or outperforming offline methods on temporal classification tasks. The efficiency and robustness of FPTT enable us to directly train a deep and performant spiking neural network for joint object localization and recognition, demonstrating the ability to train large-scale dynamic and complex spiking neural network architectures. Memory efficient online training of recurrent spiking neural networks without compromising accuracy is an open challenge in neuromorphic computing. Yin and colleagues demonstrate that training a recurrent neural network consisting of so-called liquid time-constant spiking neurons using an algorithm called Forward-Propagation Through Time allows for online learning and state-of-the-art performance at a reduced computational cost compared with existing approaches.

QoS-Aware Machine Learning Task Offloading and Power Control in Internet of Drones

Internet of drone (IoD), where drones act as the internet of things (IoT) devices, provides multiple services such as object recognition, traffic monitoring, and disaster rescue. The service response time is limited by drones’ onboard computing power, hence greatly affecting the quality of service (QoS). Machine learning (e.g., image processing) task offloading to the fog node attached to the ground base station can help reduce workload from drones and hence decrease service time. The communication latency between drones and the fog node during task offloading also affects the service time and hence the communication efficiency needs to be considered. Therefore, in this work, we consider the joint optimization of machine learning task offloading and power control in IoD to determine each drone’s number of offloaded images and wireless transmission power. We analyze the energy model of the commonly used convolutional neural network (CNN) for object recognition, and formulate the joint optimization problem as a mixed integer non-linear programming (MINLP) problem to minimize drones’ average service time constrained by drones’ energy budgets. An approximation algorithm with low computational complexity is then designed to address the problem and its performances are compared with the lower bounds and demonstrated via extensive simulations.

Convolutional Neural Networks for Object Detection and Recognition

One of the essential technologies in the fields of target extraction, pattern recognition, and motion measurement is moving object detection. Finding moving objects or a number of moving objects across a series of frames is called object tracking. Basically, object tracking is a difficult task. Unexpected changes in the surroundings, an item's mobility, noise, etc., might make it difficult to follow an object. Different tracking methods have been developed to solve these issues. This paper discusses a number of object tracking and detection approaches. The major methods for identifying objects in images will be discussed in this paper. Recent years have seen impressive advancements in fields like pattern recognition and machine learning, both of which use convolutional neural networks (CNNs). It is mostly caused by graphics processing units'(GPUs) enhanced parallel processing capacity. This article describes many kinds of object classification, object racking, and object detection techniques. Our results showed that the suggested algorithm can detect moving objects reliably and efficiently in a variety of situations.