Self-Correction Ship Tracking and Counting with Variable Time Window Based on YOLOv3
TL;DR: In this paper, the YOLOv3 pretraining model is used for ship detection, recognition, and counting in the context of intelligent maritime surveillance, timely ocean rescue, and computer-aided decision-making.
Abstract: Automatic ship detection, recognition, and counting are crucial for intelligent maritime surveillance, timely ocean rescue, and computer-aided decision-making. YOLOv3 pretraining model is used for ...
Citations
More filters
TL;DR: In this article , a deep learning approach to detect the ships from satellite imagery is discussed. But, the model developed in this work achieves integrity by the inclusion of hashing, which allows secure transmission of highly confidential images that are tamperproof.
Abstract: Ship detection plays a crucial role in marine security in remote sensing imagery. This paper discusses about a deep learning approach to detect the ships from satellite imagery. The model developed in this work achieves integrity by the inclusion of hashing. This model employs a supervised image classification technique to classify images, followed by object detection using You Only Look Once version 3 (YOLOv3) to extract features from deep CNN. Semantic segmentation and image segmentation is done to identify object category of each pixel using class labels. Then, the concept of hashing using SHA-256 is applied in conjunction with the ship count and location of bounding box in satellite image. The proposed model is tested on a Kaggle Ships dataset, which consists of 231,722 images. A total of 70% of this data is used for training, and the 30% is used for testing. To add security to images with detected ships, the model is enhanced by hashing using SHA-256 algorithm. Using SHA-256, which is a one-way hash, the data are split up into blocks of 64 bytes. The input data to the hash function are both the ship count and bounding box location. The proposed model achieves integrity by using SHA-256. This model allows secure transmission of highly confidential images that are tamper-proof.
30 citations
TL;DR: This paper introduces the computer image processing technology based on deep learning, and the specific process is divided into three steps: first, the video sampling is carried out by the UAV to obtain a large number of pictures of the ship draft reading face, and these images are preprocessed; then, the deep learning target detection algorithm of improved YOLOv3 is used to process the images to predict the position of the waterline and identify the draft characters.
Abstract: The reading of the ship draft is an important step in the process of weighing and pricing. The traditional detection method is time-consuming and labor-consuming, and it is easy to lead to misdetection. In order to solve the above problems, this paper introduces the computer image processing technology based on deep learning, and the specific process is divided into three steps: first, the video sampling is carried out by the UAV to obtain a large number of pictures of the ship draft reading face, and the images are preprocessed; then, the deep learning target detection algorithm of improved YOLOv3 is used to process the images to predict the position of the waterline and identify the draft characters; finally, the prediction results are analyzed and processed to obtain the final reading results. The experimental results show that the ship draft reading method proposed in this paper has obvious effects. The method has a good detection effect on high-quality images, and the accuracy rate can reach 98%. The accuracy rate can also reach 73% for the images with poor quality caused by improper capture, character corrosion, bad weather, etc. This method is a kind of artificial intelligence method with safe measurement process, high measurement effect, and accuracy, providing a new idea for related research.
7 citations
TL;DR: The experiment compares the moving target detection of UAV vision and the traditional target detection in four aspects: recognition accuracy, recognition speed, manual time, and divergent results.
Abstract: The detection of moving objects by machine vision is a hot research direction in recent years. It is widely used in military, medical, transportation, and agriculture. With the rapid development of UAV technology, as well as the high mobility of UAVs and the wide range of high-altitude vision, the target detection technology based on UAV vision is applied to traffic management such as vehicle tracking and detection of vehicle violations. The moving target detection technology in this study is based on the YOLOv3 algorithm. It implements moving vehicle tracking by means of Mean-Shift and Kalman filtering. In this paper, the Gaussian background difference technology is used to analyze the illegal behavior of the vehicle, and the color feature extraction technology is used to identify and locate the license plate, and the information of the illegal vehicle is entered into the database. The experiment compares the moving target detection of UAV vision and the traditional target detection in four aspects: recognition accuracy, recognition speed, manual time, and divergent results. The results show that the average accuracy rates of UAV vision-based moving target detection and traditional pattern recognition are 98.4% and 87.8%, respectively. The recognition speeds are 24.9 (vehicles/sec) and 10.6 (vehicles/sec), respectively. However, the artificial time and divergence results of moving target detection based on UAV vision are only 1/3 of the traditional mode. The moving target detection based on UAV vision has a better moving target detection ability.
5 citations
TL;DR: Wang et al. as mentioned in this paper proposed a novel framework called YOLOX-Birth Growth Death (Y-BGD) for automatic and accurate cage-free broiler counting, which cooperated with improved multiple-object tracking algorithm to ease tracking loss and counting error.
Abstract: Automatic and accurate broiler counting plays a key role in the intelligent management of the cage-free broiler breeding industry. However, severe occlusion, similar appearance, variational posture and extremely crowded situation make it a very challenging task to accurately count cage-free broilers by applying the computer vision method. Currently, many broiler breeding enterprises have to count broilers manually, resulting in high management costs. To address these challenges, we propose a novel framework called YOLOX-Birth Growth Death (Y-BGD) for automatic and accurate cage-free broiler counting. The proposed method cooperated with improved multiple-object tracking algorithm to ease tracking loss and counting error by adopting BGD data association strategy. First, to evaluate the proposed framework, we constructed a large-scale dataset (namely ChickenRun-2022) that contains 283 videos, 343,657 label boxes, and over 144,000 frames with 14,373 chicken instances in total. Next, we conducted extensive experiments and analyses on this dataset and compared it with existing representative tracking algorithms to demonstrate the effectiveness of the proposed framework. Finally, the proposed framework yielded 98.131% counting accuracy, 0.1291 GEH, and 58.98 FPS speed on ChickenRun-2022. In conclusion, the proposed method provides an automatic approach to counting the number of cage-free broiler chickens in videos with higher speed and greater accuracy, which will benefit the broiler breeding industry and precision chicken management.
3 citations
TL;DR: A vessel speed extraction framework, based on Unmanned Aerial Vehicle (UAV) airborne video, has an excellent performance with average speed measurement accuracy is above 93% in complex waters and paves a way to further predict ship traffic flow in water transportation.
Abstract: In the water transportation, ship speed estimation has become a key subject of intelligent shipping research. Traditionally, Automatic Identification System (AIS) is used to extract the ship speed information. However, transportation environment is gradually becoming complex, especially in the busy water, leading to the loss of some AIS data and resulting in a variety of maritime accidents. To make up for this deficiency, this paper proposes a vessel speed extraction framework, based on Unmanned Aerial Vehicle (UAV) airborne video. Firstly, YOLO v4 is employed to detect the ship targets in UAV image precisely. Secondly, a simple online and real time tracking method with a Deep association metric (Deep SORT) is applied to track ship targets with high quality. Finally, the ship motion pixel is computed based on the bounding box information of the ship trajectories, at the same time, the ship speed is estimated according to the mapping relationship between image space and the real space. Exhaustive experiments are conducted on the various scenarios. Results verify that the proposed framework has an excellent performance with average speed measurement accuracy is above 93% in complex waters. This paper also paves a way to further predict ship traffic flow in water transportation.
2 citations
References
More filters
21 Jun 1994
TL;DR: A feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world are proposed.
Abstract: No feature-based vision system can work unless good features can be identified and tracked from frame to frame. Although tracking itself is by and large a solved problem, selecting features that can be tracked well and correspond to physical points in the world is still hard. We propose a feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world. These methods are based on a new tracking algorithm that extends previous Newton-Raphson style search methods to work under affine image transformations. We test performance with several simulations and experiments. >
8,432 citations
23 Jun 2013
TL;DR: Large scale experiments are carried out with various evaluation criteria to identify effective approaches for robust tracking and provide potential future research directions in this field.
Abstract: Object tracking is one of the most important components in numerous applications of computer vision. While much progress has been made in recent years with efforts on sharing code and datasets, it is of great importance to develop a library and benchmark to gauge the state of the art. After briefly reviewing recent advances of online object tracking, we carry out large scale experiments with various evaluation criteria to understand how these algorithms perform. The test image sequences are annotated with different attributes for performance evaluation and analysis. By analyzing quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.
3,828 citations
13 Jun 2010
TL;DR: A new type of correlation filter is presented, a Minimum Output Sum of Squared Error (MOSSE) filter, which produces stable correlation filters when initialized using a single frame, which enables the tracker to pause and resume where it left off when the object reappears.
Abstract: Although not commonly used, correlation filters can track complex objects through rotations, occlusions and other distractions at over 20 times the rate of current state-of-the-art techniques. The oldest and simplest correlation filters use simple templates and generally fail when applied to tracking. More modern approaches such as ASEF and UMACE perform better, but their training needs are poorly suited to tracking. Visual tracking requires robust filters to be trained from a single frame and dynamically adapted as the appearance of the target object changes. This paper presents a new type of correlation filter, a Minimum Output Sum of Squared Error (MOSSE) filter, which produces stable correlation filters when initialized using a single frame. A tracker based upon MOSSE filters is robust to variations in lighting, scale, pose, and nonrigid deformations while operating at 669 frames per second. Occlusion is detected based upon the peak-to-sidelobe ratio, which enables the tracker to pause and resume where it left off when the object reappears.
2,948 citations
27 Jun 2016
TL;DR: It is shown that a simple tracker combining complementary cues in a ridge regression framework can operate faster than 80 FPS and outperform not only all entries in the popular VOT14 competition, but also recent and far more sophisticated trackers according to multiple benchmarks.
Abstract: Correlation Filter-based trackers have recently achieved excellent performance, showing great robustness to challenging situations exhibiting motion blur and illumination changes. However, since the model that they learn depends strongly on the spatial layout of the tracked object, they are notoriously sensitive to deformation. Models based on colour statistics have complementary traits: they cope well with variation in shape, but suffer when illumination is not consistent throughout a sequence. Moreover, colour distributions alone can be insufficiently discriminative. In this paper, we show that a simple tracker combining complementary cues in a ridge regression framework can operate faster than 80 FPS and outperform not only all entries in the popular VOT14 competition, but also recent and far more sophisticated trackers according to multiple benchmarks.
1,285 citations
08 Oct 2016
TL;DR: This work proposes a method for offline training of neural networks that can track novel objects at test-time at 100 fps, which is significantly faster than previous methods that use neural networks for tracking, which are typically very slow to run and not practical for real-time applications.
Abstract: Machine learning techniques are often used in computer vision due to their ability to leverage large amounts of training data to improve performance. Unfortunately, most generic object trackers are still trained from scratch online and do not benefit from the large number of videos that are readily available for offline training. We propose a method for offline training of neural networks that can track novel objects at test-time at 100 fps. Our tracker is significantly faster than previous methods that use neural networks for tracking, which are typically very slow to run and not practical for real-time applications. Our tracker uses a simple feed-forward network with no online training required. The tracker learns a generic relationship between object motion and appearance and can be used to track novel objects that do not appear in the training set. We test our network on a standard tracking benchmark to demonstrate our tracker’s state-of-the-art performance. Further, our performance improves as we add more videos to our offline training set. To the best of our knowledge, our tracker (Our tracker is available at http://davheld.github.io/GOTURN/GOTURN.html) is the first neural-network tracker that learns to track generic objects at 100 fps.
941 citations