Deep Learning Object Detection Algorithm Research Articles

An AI-in-Loop Fuzzy-Control Technique for UAV’s Stabilization and Landing

In this paper, an adaptable fuzzy control mechanism for an Unmanned Aerial Vehicle (UAV) to manipulate its mechanical actuators is provided. The mission (landing) for the UAV is defined to track (land on) an object that is detected by a deep learning object detection algorithm. The inputs of the controller are the location and speed of the UAV that has been calculated based on the location of the detected object.Two separate fuzzy controllers are proposed to control the UAV motor throttle and its roll and pitch over the mission and landing time. Fuzzy logic controller (FLC) is an intelligent controller that can be used to compensate for the non-linearity behaviour of the UAV by designing a specific fuzzy rule base. These rules will be utilized to adjust the control parameters during the mission and landing period in runtime. To add the effect of the ground for tuning the FLC membership function over the landing operation, a computational flow dynamic (CFD) modeling has been investigated. The proposed techniques is evaluated on MATLAB/Simulink simulation platform and real environment. Statistical analysis of the UAV location reported during stabilization and landing process, on both simulation and real platform, shows that the proposed technique outperforms the similar state-of-art control techniques for both mission and landing control.

A Study on Building a “Real-Time Vehicle Accident and Road Obstacle Notification Model” Using AI CCTV

This research produced a model that detects abnormal phenomena on the road, based on deep learning, and proposes a service that can prevent accidents because of other cars and traffic congestion. After extracting accident images based on traffic accident video data by using FFmpeg for model production, car collision types are classified, and only the head-on collision types are processed by using the deep learning object-detection algorithm YOLO (You Only Look Once). Using the car accident detection model that we built and the provided road obstacle-detection model, we programmed, for when the model detects abnormalities on the road, warning notification and photos that captures the accidents or obstacles, which are then transferred to the application. The proposed service was verified through application notification simulations and virtual experiments using CCTVs in Daegu, Busan, and Gwangju. By providing services, the goal is to improve traffic safety and achieve the development of a self-driving vehicle sector. As a future research direction, it is suggested that an efficient CCTV control system be introduced for the transportation environment.

A Robust Detector for Automated Welding Seam Tracking System

AbstractAccurate locating of the weld seam under strong noise is the biggest challenge for automated welding. In this paper, we construct a robust seam detector on the framework of deep learning object detection algorithm. The representative object algorithm, a single shot multibox detector (SSD), is studied to establish the seam detector framework. The improved SSD is applied to seam detection. Under the SSD object detection framework, combined with the characteristics of the seam detection task, the multifeature combination network (MFCN) is proposed. The network comprehensively utilizes the local information and global information carried by the multilayer features to detect a weld seam and realizes the rapid and accurate detection of the weld seam. To solve the problem of single-frame seam image detection algorithm failure under continuous super-strong noise, the sequence image multifeature combination network (SMFCN) is proposed based on the MFCN detector. The recurrent neural network (RNN) is used to learn the temporal context information of convolutional features to accurately detect the seam under continuous super-noise. Experimental results show that the proposed seam detectors are extremely robust. The SMFCN can maintain extremely high detection accuracy under continuous super-strong noise. The welding results show that the laser vision seam tracking system using the SMFCN can ensure that the welding precision meets industrial requirements under a welding current of 150 A.

Automotive Brake Part Inspection and Fault Localization using Deep Learning

Inspection of brake components is very essential to detect the damaged manufactured parts before it is assembled in any vehicle. Manual inspection of brakes is extremely difficult since most of defects are very minute and cannot be identified by human eyes. Therefore, automatic inspection of manufactured brakes is indispensible to prevent failure of brakes and accidents. Previously, various research articles perform inspection of brake through conventional image processing and traditional image processing algorithms. However, these techniques are capable of identifying a single fault only and are less robust to detecting numerous faults. Further, the existing techniques hardly localize the exact location of faults in the surface of brake. In order to over these drawbacks, in this research we utilize deep learning object detection algorithms namely Single Shot Detector and Faster RCNN to identify and localize the exact location of fault on the brake surface. Furthermore, the proposed system is capable to detect different types of faults in a single algorithm and is robust to brake’s material surface, environmental and lightening factors. The deep learning algorithms are trained using transfer learning on custom collected dataset. The proposed algorithms deliver an accuracy of 95.64% and mAP of 73.2% on cylindrical grey shade brakes.

A New Approach for Navigation and Traffic Signs Indication Using Map Integrated Augmented Reality for Self-Driving Cars

Self-driving vehicles are one of the emerging technologies. This technology has potential to save lives and make lives comfortable. However, the technology used in self driving cars has to perform series of task for building perceptions. This has some certain prerequisites related to road infrastructure and is affected by daylight and weather conditions of the place. If these prerequisites are not satisfied then it could affect the performance of the vehicle and can be considered as compromise with safety of the users. This research work is focused on trying to find a new approach using which the underdeveloped countries will also be able to implement self driving cars in their county. The objective of this paper is to propose a new approach to supplement the technology used in the self-driving cars for perception. Using this approach the countries who don’t satisfy the prerequisites would be eligible to implement them without compromising the safety.The proposed approach uses the technology Augmented Reality to create and augment artificial objects of navigational signs and traffic signals based on vehicles location to reality. Later the augmented scene is fed into the conventional Deep learning object detection algorithm to detect the navigational artificial objected along with other real objects. This approach help navigate the vehicle even if the road infrastructure does not have very good sign indications and marking.The approach was tested locally by creating a local navigational system and a smartphone based augmented reality app. The approach performed better than the conventional method as the objects were clearer in the frame which made it each for the object detection to detect them.

Soft-Weighted-Average Ensemble Vehicle Detection Method Based on Single-Stage and Two-Stage Deep Learning Models

The deep learning object detection algorithms have become one of the powerful tools for road vehicle detection in autonomous driving. However, the limitation of the number of high-quality labeled training samples makes the single-object detection algorithms unable to achieve satisfactory accuracy in road vehicle detection. In this paper, by comparing the pros and cons of various object detection algorithms, two different algorithms with a different emphasis are selected for a weighted ensemble. Besides, a new ensemble method named the Soft-Weighted-Average method is proposed. The proposed method is attenuated by the confidence, and it “punishes” the detection result of the corresponding relationship by the confidence attenuation, instead of by deleting the output of a certain model. The proposed method can further reduce the vehicle misdetection of the target detection algorithm, obtaining a better detection result. Lastly, the ensemble method can achieve an average accuracy of 94.75% for simple targets, which makes it the third-ranked method in the KITTI evaluation system.

Detecting Multi C lass Artifacts in Endoscopic I mages u sing YOLOv3

Endoscopy is a regular, clinical non-surgical procedure to examine hollow organs like esophagus, stomach, intestine, etc., Nowadays, due to rapid technological development and miniaturization of hardware endoscopy can be performed in the respiratory tract, urinary tract, female reproductive tract and joints apart from gastrointestinal (GI) tract. The need for GI endoscopy is to examine, and diagnose ailments like cancers, polyps, and assist cauterizing bleeding vessels. The organ nature creates lots of artifacts in the imaged tissue such as saturation, specularity, blur, contrast, bubbles, and debris which causes significant challenges in quantitative analysis. Thus, combining state-of-the-art deep learning object detection algorithms like YOLOv3 with endoscopy leads to efficient and accurate localization and categorization of different imaging artifacts. This paper presents a detailed implementation of YOLOv3 in detecting endoscopic artifacts. Intensive training in a GPU enabled environment (Google COLAB) was carried out. The experimental results of the algorithm achieve mAP% of 55.18 for identifying the artifacts in endoscopic images with a prediction time of 0.0179 seconds on test images.

Simple weakly supervised deep learning pipeline for detecting individual red-attacked trees in VHR remote sensing images

ABSTRACT After an attack the by pine wood nematode, pine tree needles turn red. Using convolutional neural networks (CNNs) based object detection methods, machines can detect red-attacked trees. However, most deep learning object detection algorithms (such as Faster R-CNN and YOLO among others) often require a large number of labelled training datasets, where in each image every object must be given a bounding box label. To increase the cost-effectiveness of this process, we propose a simple yet efficient weakly supervised processing pipeline, based on class activation maps to locate the target. Unlike object detection methods that require bounding-box-labelled data for training, the proposed pipeline only needs image-level-labelled data. Using the proposed pipeline, we could achieve an average precision (AP) of 91.82% on test dataset. Comparing with sliding window-based method which achieves an average precision (AP) of 89.95%, our method not only gets a better AP but also runs faster than sliding window-based pipeline. This result not only indicates that the pipeline is a highly effective one but also demonstrates that image-level-labelled aerial images can be used for the detection of red-attacked tree. The proposed method should also find use in other object detection applications in the field of remote sensing.

Underwater and airborne monitoring of marine ecosystems and debris

Advancing the sustainable use and conservation of marine environments is urgent. Tons of debris including macro- and microplastics generated on land are entering the oceans, marine resources are decreasing, and many species are facing extinction. Though satellite remote sensing techniques are commonly used for global environmental monitoring, it is still difficult to detect small objects such as floating debris on the vast ocean surface, and the ecosystems deep in the oceans where light does not reach are unobservable. An autonomous monitoring system consisting of optimally controlled robots is required for acquiring spatiotemporally rich marine data. However, object detection in marine environments, which is a necessary function the robots should have for underwater and aerial monitoring, has not been extensively studied. Here, we argue that state-of-the-art deep-learning-based object detection works well for monitoring underwater ecosystems and marine debris. We found that by using the deep-learning object-detection algorithm YOLO v3, underwater sea life and debris floating on the ocean surface can be detected with mean average precision of 69.6% and 77.2%, respectively. We anticipate our results to be a starting point for developing tools for enabling safe and precise acquisition of marine data to elucidate and utilize this last frontier.

A Comparative Study of State-of-the-Art Deep Learning Algorithms for Vehicle Detection

In recent years, the deep learning object detection algorithms using 2D images have become the powerful tools for road object detection in autonomous driving. In fact, the deep learning methods for road vehicle detection have achieved the remarkable results. Although there have been a large number of studies that thoroughly explored various types of deep learning methods for vehicle detection, there are a few studies that compare and evaluate the detection time and detection accuracy of the mainstream deep learning object detection algorithms for vehicle detection. Here, this article compares five mainstream deep learning object detection algorithms in vehicle detection, namely the faster RCNN, R-FCN, SSD, RetinaNet, and YOLOv3 on the KITTI data and analyze the obtained results. The detection time and detection accuracy of the five object-detection algorithms on the KITTI test set are compared and analyzed; the PR curve and AP value are used to evaluate the detection accuracy.

Research on Simulation System of Small Unmanned Air-to-Ground Object Detection Platform

Air-to-ground object detection has important application value in many fields such as military reconnaissance, air strike, personnel rescue, and natural exploration. Object detection algorithm based on deep learning solves the problems of poor generality and low robustness of traditional manual detection algorithms. It has great advantages in air-to-ground detection tasks, but for small unmanned platforms, currently deep learning object detection algorithms have high hardware requirements and are difficult to deploy. In this paper, a deep learning object detection simulation system is built based on the TX2 embedded development board with the features of low power consumption, light weight and fast calculation speed. This object detection simulation experiment is performed for two mainstream deep learning object detection algorithms. The experimental results showed that the regression-based SSD algorithm combined with MobileNets feature extraction network could perform real-time in the embedded system, which laid the foundation for the actual construction of the next unmanned aerial platform.