Learning Method For Object Detection Research Articles

Joint Semantic Deep Learning Algorithm for Object Detection under Foggy Road Conditions

Current mainstream deep learning methods for object detection are generally trained on high-quality datasets, which might have inferior performances under bad weather conditions. In the paper, a joint semantic deep learning algorithm is proposed to address object detection under foggy road conditions, which is constructed by embedding three attention modules and a 4-layer UNet multi-scale decoding module in the feature extraction module of the backbone network Faster RCNN. The algorithm differs from other object detection methods in that it is designed to solve low- and high-level joint tasks, including dehazing and object detection through end-to-end training. Furthermore, the location of the fog is learned by these attention modules to assist image recovery, the image quality is recovered by UNet decoding module for dehazing, and then the feature representations of the original image and the recovered image are fused and fed into the FPN (Feature Pyramid Network) module to achieve joint semantic learning. The joint semantic features are leveraged to push the subsequent network modules ability, and therefore make the proposed algorithm work better for the object detection task under foggy conditions in the real world. Moreover, this method and Faster RCNN have the same testing time due to the weight sharing in the feature extraction module. Extensive experiments confirm that the average accuracy of our algorithm outperforms the typical object detection algorithms and the state-of-the-art joint low- and high-level tasks algorithms for the object detection of seven kinds of objects on road traffics under normal weather or foggy conditions.

Aircraft detection in satellite imagery using deep learning-based object detectors

Over the recent years, object detection in satellite imagery has become a crucial task in remote sensing applications. Specifically, the detection of aircraft is critical for military scenarios. Numerous computer vision techniques have been applied for this problem, however, robust and efficient detection of aircraft in satellite imagery poses several challenges, such as, variance of color, size, aspect ratio and orientation of aircraft and complex backgrounds. In this paper, we provide an in-depth review of deep learning methods for object detection applied to aircraft detection including both conventional and state-of-the-art techniques. We also provide a comprehensive experimental and comparative analysis of deep learning-based object detectors including Region-based CNN (RCNN), Fast RCNN, Faster RCNN and You Only Look Once (YOLO) encapsulating the most cited feature extraction networks including Alexnet, VGG-16, Resnet-18, Resnet-50, Resnet-101 and Inception-v3. The detailed quantitative comparison allows for selection of the most suitable set of object detector, backbone feature extraction network and hyperparameters for aircraft detection in satellite imagery with trade-off options between precision and detection time. The evaluation is based on mean average precision (mAP), precision versus recall, time complexity and computational complexity. Finally, we draw our conclusions and identify promising future work.

Different Plant Disease Detection and Pest Control Techniques Using Image Processing

Abstract: Tomato is one of the most important fruit vegetable in our daily life. 80% of kitchens uses Tomato. but there are some diseases and some disorders on the tomato plant. To overcome this problems many of technologies are used. Such as image processing , feature extraction ,feature classification are used as traditional method, also the end to end structure is used to simplified recognition process and overcome problems. Here we are using the deep learning method for object detection .it saves time and effort .also it gives the accuracy to reduce the huge losses caused by diseases and pest.in deep learning method Convolutional Neural Network (CNN) is used. the datasets are the real images of tomato plants are taken. Through the above research the identification and detection of disease of tomato plant is quickly done. It is an engineering application for plant disease detection and pest control.

YOLOv4-Lite–Based Urban Plantation Tree Detection and Positioning With High-Resolution Remote Sensing Imagery

Automatic tree identification and position using high-resolution remote sensing images are critical for ecological garden planning, management, and large-scale environmental quality detection. However, existing single-tree detection methods have a high rate of misdetection in forests not only due to the similarity of background and crown colors but also because light and shadow caused abnormal crown shapes, resulting in a high rate of misdetections and missed detection. This article uses urban plantations as the primary research sample. In conjunction with the most recent deep learning method for object detection, a single-tree detection method based on the lite fourth edition of you only look once (YOLOv4-Lite) was proposed. YOLOv4’s object detection framework has been simplified, and the MobileNetv3 convolutional neural network is used as the primary feature extractor to reduce the number of parameters. Data enhancement is performed for categories with fewer single-tree samples, and the loss function is optimized using focal loss. The YOLOv4-Lite method is used to detect single trees on campus, in an orchard, and an economic plantation. Not only is the YOLOv4-Lite method compared to traditional methods such as the local maximum value method and the watershed method, where it outperforms them by nearly 46.1%, but also to novel methods such as the Chan-Vese model and the template matching method, where it outperforms them by nearly 26.4%. The experimental results for single-tree detection demonstrate that the YOLOv4-Lite method improves accuracy and robustness by nearly 36.2%. Our work establishes a reference for the application of YOLOv4-Lite in additional agricultural and plantation products.

Central Courtyard Feature Extraction in Remote Sensing Aerial Images Using Deep Learning: A Case-Study of Iran

Central courtyards are primary components of vernacular architecture in Iran. The directions, dimensions, ratios, and other characteristics of central courtyards are critical for studying historical passive cooling and heating solutions. Several studies on central courtyards have compared their features in different cities and climatic zones in Iran. In this study, deep learning methods for object detection and image segmentation are applied to aerial images, to extract the features of central courtyards. The case study explores aerial images of nine historical cities in Bsk, Bsh, Bwk, and Bwh Köppen climate zones. Furthermore, these features were gathered in an extensive dataset, with 26,437 samples and 76 geometric and climatic features. Additionally, the data analysis methods reveal significant correlations between various features, such as the length and width of courtyards. In all cities, the correlation coefficient between these two characteristics is approximately +0.88. Numerous mathematical equations are generated for each city and climate zone by fitting the linear regression model to these data in different cities and climate zones. These equations can be used as proposed design models to assist designers and researchers in predicting and locating the best courtyard houses in Iran’s historical regions.

Toward Robotic Weed Control: Detection of Nutsedge Weed in Bermudagrass Turf Using Inaccurate and Insufficient Training Data

To enable robotic weed control, we develop algorithms to detect nutsedge weed from bermudagrass turf. Due to the similarity between the weed and the background turf, manual data labeling is expensive and error-prone. Consequently, directly applying deep learning methods for object detection cannot generate satisfactory results. Building on an instance detection approach (i.e. Mask R-CNN), we combine synthetic data with raw data to train the network. We propose an algorithm to generate high fidelity synthetic data, adopting different levels of annotations to reduce labeling cost. Moreover, we construct a nutsedge skeleton-based probabilistic map (NSPM) as the neural network input to reduce the reliance on pixel-wise precise labeling. We also modify loss function from cross entropy to Kullback-Leibler divergence which accommodates uncertainty in the labeling process. We implement the proposed algorithm and compare it with both Faster R-CNN and Mask R-CNN. The results show that our design can effectively overcome the impact of imprecise and insufficient training sample issues and significantly outperform the Faster R-CNN counterpart with a false negative rate of only 0.4%. In particular, our approach also reduces labeling time by 95% while achieving better performance if comparing with the original Mask R-CNN approach.

Continual Learning Strategy in One-Stage Object Detection Framework Based on Experience Replay for Autonomous Driving Vehicle.

Object detection is an important aspect for autonomous driving vehicles (ADV), which may comprise of a machine learning model that detects a range of classes. As the deployment of ADV widens globally, the variety of objects to be detected may increase beyond the designated range of classes. Continual learning for object detection essentially ensure a robust adaptation of a model to detect additional classes on the fly. This study proposes a novel continual learning method for object detection that learns new object class(es) along with cumulative memory of classes from prior learning rounds to avoid any catastrophic forgetting. The results of PASCAL VOC 2007 have suggested that the proposed ER method obtains 4.3% of mAP drop compared against the all-classes learning, which is the lowest amongst other prior arts.

A Learning Method for Object Detection from Low Resolution Image

Object recognition the use deep neural networks has been most typically used in real applications. We propose a framework for identifying items in pics of very low decision through collaborative studying of two deep neural networks. It includes photo enhancement network object popularity networks. The picture correction community seeks to decorate images of much lower decision faster and more informative images with the usages of collaborative gaining knowledge of indicatores from object recognition networks. Object popularity networks actively participate in the mastering of photograph enhancement networks, with skilled weights for photographs of excessive resolution. It uses output from photograph enhancement networks as augmented studying recordes to reinforce the overall performance of its identity on a very low decision object. We esablished that the proposed method can improve photograph reconstruction and classification overall performance.

Apple Detection in Natural Environment Using Deep Learning Algorithms

It is a challenging problem to detect the apple in natural environment using traditional object recognition algorithms due to occlusion, fluctuating illumination and complex backgrounds. Deep learning methods for object detection make impressive progress, which can automatically extract the number, pixel position, size and other features of apples from the images. In this paper, four deep learning recognition models, Faster RCNN based on AlexNet, Faster RCNN based on ResNet101, YOLOv3 based on DarkNet53 and improved YOLOv3 were employed to carry out recognition experiments on red and green apple under three illumination and two image sharpness conditions, with the transfer learning to accelerate the training process. The results showed that improved YOLOv3 model had the best recognition effect among the four detection models. F1 value of red apple recognition was 95.0%, 94.6% and 94.1% for normal, insufficient and excessive illumination, respectively, and F1 value of green apple recognition was 94.9%, 94.0% and 91.1%. There were F1 value of 92.8% and 92.1% for red and green apple recognition in blurred images, respectively. Moreover, improved YOLOv3 algorithm still had the better performance for occlusion, spot, overlap and incomplete apples, with a recognition recall rate higher than 88.5%. It can be concluded that improved YOLOv3 algorithm can provide a more efficient way for apple detection in natural environment.

Assessment of CNN-Based Methods for Individual Tree Detection on Images Captured by RGB Cameras Attached to UAVs.

Detection and classification of tree species from remote sensing data were performed using mainly multispectral and hyperspectral images and Light Detection And Ranging (LiDAR) data. Despite the comparatively lower cost and higher spatial resolution, few studies focused on images captured by Red-Green-Blue (RGB) sensors. Besides, the recent years have witnessed an impressive progress of deep learning methods for object detection. Motivated by this scenario, we proposed and evaluated the usage of Convolutional Neural Network (CNN)-based methods combined with Unmanned Aerial Vehicle (UAV) high spatial resolution RGB imagery for the detection of law protected tree species. Three state-of-the-art object detection methods were evaluated: Faster Region-based Convolutional Neural Network (Faster R-CNN), YOLOv3 and RetinaNet. A dataset was built to assess the selected methods, comprising 392 RBG images captured from August 2018 to February 2019, over a forested urban area in midwest Brazil. The target object is an important tree species threatened by extinction known as Dipteryx alata Vogel (Fabaceae). The experimental analysis delivered average precision around 92% with an associated processing times below 30 miliseconds.

Past, present and future approaches using computer vision for animal re‐identification from camera trap data

Abstract The ability of a researcher to re‐identify (re‐ID) an individual animal upon re‐encounter is fundamental for addressing a broad range of questions in the study of ecosystem function, community and population dynamics and behavioural ecology. Tagging animals during mark and recapture studies is the most common method for reliable animal re‐ID; however, camera traps are a desirable alternative, requiring less labour, much less intrusion and prolonged and continuous monitoring into an environment. Despite these advantages, the analyses of camera traps and video for re‐ID by humans are criticized for their biases related to human judgement and inconsistencies between analyses. In this review, we describe a brief history of camera traps for re‐ID, present a collection of computer vision feature engineering methodologies previously used for animal re‐ID, provide an introduction to the underlying mechanisms of deep learning relevant to animal re‐ID, highlight the success of deep learning methods for human re‐ID, describe the few ecological studies currently utilizing deep learning for camera trap analyses and our predictions for near future methodologies based on the rapid development of deep learning methods. For decades, ecologists with expertise in computer vision have successfully utilized feature engineering to extract meaningful features from camera trap images to improve the statistical rigor of individual comparisons and remove human bias from their camera trap analyses. Recent years have witnessed the emergence of deep learning systems which have demonstrated the accurate re‐ID of humans based on image and video data with near perfect accuracy. Despite this success, ecologists have yet to utilize these approaches for animal re‐ID. By utilizing novel deep learning methods for object detection and similarity comparisons, ecologists can extract animals from an image/video data and train deep learning classifiers to re‐ID animal individuals beyond the capabilities of a human observer. This methodology will allow ecologists with camera/video trap data to reidentify individuals that exit and re‐enter the camera frame. Our expectation is that this is just the beginning of a major trend that could stand to revolutionize the analysis of camera trap data and, ultimately, our approach to animal ecology.

A fast online incremental learning method for object detection and pose classification using voting and combined appearance modeling

This paper presents a novel and rapid object detection method that identifies object positions and classifies object views. To overcome the limitations of appearance-based object recognition, we integrate a spatial relationship between local key points and object center position. A voting technique is applied to estimate the object area and then construct a bounding box to capture the object. A combined appearance model is introduced by a recall image to help deal with false detection problems. Experimental results show that our method can improve the object detection time while still preserving the average precision results. Moreover, our method can improve the accuracy of view classification.