An Evaluation Metric for Object Detection Algorithms in Autonomous Navigation Systems and its Application to a Real-Time Alerting System

Abstract Surface data measurement and analysis are an established mean of detecting drillstring low-frequency torsional vibration or stick-slip. The industry has also developed models that link surface torque and downhole drill bit rotational speed. Cameras provide an alternative noninvasive approach to existing wired/wireless sensors used to gather such surface data. The results of a preliminary field assessment of drilling dynamics utilizing camera-based drillstring monitoring are presented in this work. Detection and timing of events from the video are performed using computer vision techniques and object detection algorithms. A real-time interest point tracker utilizing homography estimation and sparse optical flow point tracking is deployed. We use a fully convolutional deep neural network trained to detect interest points and compute their accompanying descriptors. The detected points and descriptors are matched across video sequences and used for drillstring rotation detection and speed estimation. When the drillstring's vibration is invisible to the naked eye, the point tracking algorithm is preceded with a motion amplification function based on another deep convolutional neural network. We have clearly demonstrated the potential of camera-based noninvasive approaches to surface drillstring dynamics data acquisition and analysis. Through the application of real-time object detection algorithms on rig video feed, surface events were detected and timed. We were also able to estimate drillstring rotary speed and motion profile. Torsional drillstring modes can be identified and correlated with drilling parameters and bottomhole assembly design. A novel vibration array sensing approach based on a multi-point tracking algorithm is also proposed. A vibration threshold setting was utilized to enable an additional motion amplification function providing seamless assessment for multi-scale vibration measurement. Cameras were typically devices to acquire images/videos for offline automated assessment (recently) or online manual monitoring (mainly), this work has shown how fog/edge computing makes it possible for these cameras to be "conscious" and "intelligent," hence play a critical role in automation/digitalization of drilling rigs. We showcase their preliminary application as drilling dynamics and rig operations sensors in this work. Cameras are an ideal sensor for a drilling environment since they can be installed anywhere on a rig to perform large-scale live video analytics on drilling processes.

Download Full-text

Prediction of Crime Scene Objects Using Deep Learning

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.37512 ◽

2021 ◽

Vol 9 (VIII) ◽

pp. 857-864

Author(s):

Vibhavari B Rao

Keyword(s):

Deep Learning ◽

Object Detection ◽

Computer Architecture ◽

Real Time ◽

Surveillance System ◽

Crime Scene ◽

Detection Model ◽

Detection Algorithms ◽

Performance Metric ◽

Smart Surveillance

The crime rates today can inevitably put a civilian's life in danger. While consistent efforts are being made to alleviate crime, there is also a dire need to create a smart and proactive surveillance system. Our project implements a smart surveillance system that would alert the authorities in real-time when a crime is being committed. During armed robberies and hostage situations, most often, the police cannot reach the place on time to prevent it from happening, owing to the lag in communication between the informants of the crime scene and the police. We propose an object detection model that implements deep learning algorithms to detect objects of violence such as pistols, knives, rifles from video surveillance footage, and in turn send real-time alerts to the authorities. There are a number of object detection algorithms being developed, each being evaluated under the performance metric mAP. On implementing Faster R-CNN with ResNet 101 architecture we found the mAP score to be about 91%. However, the downside to this is the excessive training and inferencing time it incurs. On the other hand, YOLOv5 architecture resulted in a model that performed very well in terms of speed. Its training speed was found to be 0.012 s / image during training but naturally, the accuracy was not as high as Faster R-CNN. With good computer architecture, it can run at about 40 fps. Thus, there is a tradeoff between speed and accuracy and it's important to strike a balance. We use transfer learning to improve accuracy by training the model on our custom dataset. This project can be deployed on any generic CCTV camera by setting up a live RTSP (real-time streaming protocol) and streaming the footage on a laptop or desktop where the deep learning model is being run.

Download Full-text

Performance Evaluation of Real-Time Object Detection Algorithms

2019 7th International Electrical Engineering Congress (iEECON) ◽

10.1109/ieecon45304.2019.8938687 ◽

2019 ◽

Cited By ~ 1

Author(s):

Sanun Srisuk ◽

Chanwit Suwannapong ◽

Songrit Kitisriworapan ◽

Apiwut Kaewsong ◽

Surachai Ongkittikul

Keyword(s):

Performance Evaluation ◽

Object Detection ◽

Real Time ◽

Detection Algorithms

Download Full-text

Zero-Shot Pipeline Detection for Sub-Bottom Profiler Data Based on Imaging Principles

Remote Sensing ◽

10.3390/rs13214401 ◽

2021 ◽

Vol 13 (21) ◽

pp. 4401

Author(s):

Gen Zheng ◽

Jianhu Zhao ◽

Shaobo Li ◽

Jie Feng

Keyword(s):

Standard Deviation ◽

Object Detection ◽

Real Time ◽

Synthesis Method ◽

Vertical Direction ◽

Mean Deviation ◽

The Real ◽

Detection Algorithms ◽

Underwater Pipeline ◽

Time Requirements

With the increasing number of underwater pipeline investigation activities, the research on automatic pipeline detection is of great significance. At this stage, object detection algorithms based on Deep Learning (DL) are widely used due to their abilities to deal with various complex scenarios. However, DL algorithms require massive representative samples, which are difficult to obtain for pipeline detection with sub-bottom profiler (SBP) data. In this paper, a zero-shot pipeline detection method is proposed. First, an efficient sample synthesis method based on SBP imaging principles is proposed to generate samples. Then, the generated samples are used to train the YOLOv5s network and a pipeline detection strategy is developed to meet the real-time requirements. Finally, the trained model is tested with the measured data. In the experiment, the trained model achieved a [email protected] of 0.962, and the mean deviation of the predicted pipeline position is 0.23 pixels with a standard deviation of 1.94 pixels in the horizontal direction and 0.34 pixels with a standard deviation of 2.69 pixels in the vertical direction. In addition, the object detection speed also met the real-time requirements. The above results show that the proposed method has the potential to completely replace the manual interpretation and has very high application value.

Download Full-text

Enabling Off-Road Autonomous Navigation-Simulation of LIDAR in Dense Vegetation

Electronics ◽

10.3390/electronics7090154 ◽

2018 ◽

Vol 7 (9) ◽

pp. 154 ◽

Cited By ~ 9

Author(s):

Christopher Goodin ◽

Matthew Doude ◽

Christopher Hudson ◽

Daniel Carruth

Keyword(s):

Real Time ◽

Autonomous Navigation ◽

Machine Learning Techniques ◽

Navigation Systems ◽

Ground Vehicles ◽

Navigation Simulation ◽

Learning Techniques ◽

Navigation Algorithms ◽

Processing Algorithms ◽

Solid Obstacles

Machine learning techniques have accelerated the development of autonomous navigation algorithms in recent years, especially algorithms for on-road autonomous navigation. However, off-road navigation in unstructured environments continues to challenge autonomous ground vehicles. Many off-road navigation systems rely on LIDAR to sense and classify the environment, but LIDAR sensors often fail to distinguish navigable vegetation from non-navigable solid obstacles. While other areas of autonomy have benefited from the use of simulation, there has not been a real-time LIDAR simulator that accounted for LIDAR–vegetation interaction. In this work, we outline the development of a real-time, physics-based LIDAR simulator for densely vegetated environments that can be used in the development of LIDAR processing algorithms for off-road autonomous navigation. We present a multi-step qualitative validation of the simulator, which includes the development of an improved statistical model for the range distribution of LIDAR returns in grass. As a demonstration of the simulator’s capability, we show an example of the simulator being used to evaluate autonomous navigation through vegetation. The results demonstrate the potential for using the simulation in the development and testing of algorithms for autonomous off-road navigation.

Download Full-text

A modified YOLOv3 detection method for vision-based water surface garbage capture robot

International Journal of Advanced Robotic Systems ◽

10.1177/1729881420932715 ◽

2020 ◽

Vol 17 (3) ◽

pp. 172988142093271

Author(s):

Xiali Li ◽

Manjun Tian ◽

Shihan Kong ◽

Licheng Wu ◽

Junzhi Yu

Keyword(s):

Object Detection ◽

Real Time ◽

Water Surface ◽

High Speed ◽

Detection Method ◽

Training Data ◽

Aquatic Environments ◽

Valuable Insight ◽

Data Set ◽

Detection Algorithms

To tackle the water surface pollution problem, a vision-based water surface garbage capture robot has been developed in our lab. In this article, we present a modified you only look once v3-based garbage detection method, allowing real-time and high-precision object detection in dynamic aquatic environments. More specifically, to improve the real-time detection performance, the detection scales of you only look once v3 are simplified from 3 to 2. Besides, to guarantee the accuracy of detection, the anchor boxes of our training data set are reclustered for replacing some of the original you only look once v3 prior anchor boxes that are not appropriate to our data set. By virtue of the proposed detection method, the capture robot has the capability of cleaning floating garbage in the field. Experimental results demonstrate that both detection speed and accuracy of the modified you only look once v3 are better than those of other object detection algorithms. The obtained results provide valuable insight into the high-speed detection and grasping of dynamic objects in complex aquatic environments autonomously and intelligently.

Download Full-text

Nondeterministic Criteria to Discard Redundant Information in Real Time Autonomous Navigation Systems based on Monocular Vision

10.1109/isic.2008.4635955 ◽

2008 ◽

Cited By ~ 1

Author(s):

A. Miranda Neto ◽

L. Rittner ◽

D. E. Zampieri ◽

A. Correa-Victorino

Keyword(s):

Real Time ◽

Autonomous Navigation ◽

Monocular Vision ◽

Navigation Systems ◽

Redundant Information ◽

Time Autonomous

Download Full-text

Real-Time Image Resizing Hardware Accelerator for Object Detection Algorithms

2013 International Symposium on Electronic System Design ◽

10.1109/ised.2013.26 ◽

2013 ◽

Cited By ~ 6

Author(s):

Gaurav Mishra ◽

Yan Lin Aung ◽

Meiqing Wu ◽

Siew-Kei Lam ◽

Thambipillai Srikanthan

Keyword(s):

Object Detection ◽

Real Time ◽

Hardware Accelerator ◽

Image Resizing ◽

Detection Algorithms ◽

Real Time Image ◽

Time Image

Download Full-text

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6999 ◽

2020 ◽

Vol 34 (07) ◽

pp. 12993-13000 ◽

Cited By ~ 15

Author(s):

Zhaohui Zheng ◽

Ping Wang ◽

Wei Liu ◽

Jinze Li ◽

Rongguang Ye ◽

...

Keyword(s):

Object Detection ◽

Performance Improvement ◽

Detection Algorithms ◽

Art Object ◽

Bounding Box ◽

Geometric Factors ◽

Evaluation Metric ◽

Point Distance ◽

Performance Gains ◽

Overlap Area

Bounding box regression is the crucial step in object detection. In existing methods, while ℓn-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU). Recently, IoU loss and generalized IoU (GIoU) loss have been proposed to benefit the IoU metric, but still suffer from the problems of slow convergence and inaccurate regression. In this paper, we propose a Distance-IoU (DIoU) loss by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training than IoU and GIoU losses. Furthermore, this paper summarizes three geometric factors in bounding box regression, i.e., overlap area, central point distance and aspect ratio, based on which a Complete IoU (CIoU) loss is proposed, thereby leading to faster convergence and better performance. By incorporating DIoU and CIoU losses into state-of-the-art object detection algorithms, e.g., YOLO v3, SSD and Faster R-CNN, we achieve notable performance gains in terms of not only IoU metric but also GIoU metric. Moreover, DIoU can be easily adopted into non-maximum suppression (NMS) to act as the criterion, further boosting performance improvement. The source code and trained models are available at https://github.com/Zzh-tju/DIoU.

Download Full-text