1. Introduction
The pollution of oil pollution to the environment is becoming more and more serious, the Nereids project aims to strengthen civil protection and marine pollution preparedness and cooperation among Greece and Cyprus [
1,
2]. This project has a good effect on protecting the environment. Fingas, Merv reviewed the remote-sensing of oil spills [
3]. This paper analyzed the camera, laser fluorescence sensor, radar detection and other detection means to detect oil spills. T. M. Alves combined the oil spill model with bathymetric, meteorological, oceanographic, and geomorphic data to model a series of oil spills in the eastern Mediterranean [
4]. Alves Tiago M. proposed new mathematical and geological models to mitigate potential oil spills in the eastern Mediterranean [
5]. Oil spills are serious on the environment, so the monitoring of oil spills are important [
6,
7]. Now people use video detection [
8], UAV [
9] and satellites [
10] to detect the ground area. The UAV is widely used because of their low cost and flexibility. However, the application of UAV can only record the area or detect it by human observation screen, and the identical effect of the oil pollution area is poor. In order to solve this problem, researchers use image segmentation method to segment the detected image to obtain the oil pollution area and better detect the environment [
11,
12]. Color image segmentation has always been the focus of many scholars, because color images have rich color space, which brings great challenges to the image segmentation algorithm. There are primarily four types of segmentation methods: thresholding [
13,
14,
15], boundary-based [
16,
17,
18], region-based [
19,
20], and hybrid techniques [
21,
22]. With the development of artificial neural network, more and more attention has been paid to PCNN model. It has the characteristics of global cooling and synchronous pulse, which makes it widely use in the field of image processing. PCNN, originated from Eckhorn et al. [
23] who focus on the study of the synchronous oscillation phenomenon in the visual cortex of cats, has been applied in a variety of applications in image processing [
24].
PCNN has broad applications in many aspects for image segmentation [
25]. Xiang R proposed a simplified pulse-coupled neural network, which developed based on the comentropy gradient for segmentation of tomato plant images captured at night [
26]. The proposed algorithm exhibited the optimal segmentation performance, with the best rate of 91.67%. Chen Y proposed method performs color image segmentation by a simplified pulse-coupled neural network (SPCNN) for the object model image and test image, and then conducted a region-based matching between them [
27]. SPCNN could well solve the problem of image segmentation, but due to the large number of parameters in the PCNN model, it was unable to adapt to the segmentation of different images. In order to solve the problem of PCNN with improper parameter selection and determination of circulation iterations which leaded to the image owe-segmentation or over-segmentation, Li H used an Iterative Self-organizing Data Clustering (ISODC) to resolve the problems of the PCNN parameter selection. Experimental results show that the proposed method improves the segmentation speed and achieves good segmentation results [
28]. He presented an improved PCNN model that integrated the simplified framework and spectral residual to alleviate the fairly complex determination of parameter problem [
29]. The method has high precision of the infrared pedestrian image. Lian J proposed a parameter-adaptive pulse-coupled neural network, which has a low computational complexity for different kinds of medical images and has a high segmentation precision [
30]. So, parameter selection of PCNN model plays an important role in image segmentation accuracy.
In order to solve the difficulty of parameter value assignment increases with higher performance, most researchers study how to use an optimization algorithm to solve PCNN parameters. Gao H Y proposed Quantum Geese Swarm Optimization (QGSO) evolve parameters of PCNN, experiment results show that the proposed method can obtain better segmented images and has an excellent performance [
31]. Bai W proposed a method of dividing the insulator image based on the simplified model of PCNN is proposed to extract the number of insulator sheds of a string. The method used the PSO algorithm to select the optimal PCNN parameter to realize the binary segmentation of the insulator image [
32]. Due to the differences in actual engineering problems that various meta-heuristics adapt to solve, the traditional optimization methods are often not satisfactory in computational accuracy. Therefore, the selection of optimization algorithm becomes particularly important for PCNN model parameters. There are many kinds of optimization algorithms, and each algorithm has its own advantages [
33,
34]. Yang X proposed bat algorithm, was introduced for solving engineering optimization tasks [
35,
36]. The method was based on the echolocation behavior of bats. Cheng MY proposed an algorithm called Symbiotic Organisms Search (SOS) to numerical optimization and engineering design problems [
37,
38]. SOS simulated the symbiotic interaction strategies adopted by organisms to survive and propagate in the ecosystem. Mirjalili S proposed a novel nature-inspired meta-heuristic optimization algorithm, called Whale Optimization Algorithm (WOA), which mimicked the social behavior of humpback whales [
39,
40]. In 2017, Mirjalili S proposed an optimization algorithm called Grasshopper Optimization Algorithm (GOA) and applied it to challenge problems in structural optimization [
41,
42,
43]. Wolpert, D H introduced a new optimization algorithm based on Newton’s law of cooling, as called the thermal exchange algorithm (TEO) [
44]. The algorithm mainly described that each agent was considered as a cooling object and by associating another agent as environment, a heat transferring and thermal exchange happened between them. Gaurav Dhiman presented a novel bio-inspired algorithm called a seagull optimization algorithm (SOA) for solving computationally expensive problems [
45]. The proposed algorithm is able to provide better results as compared to the other well-known metaheuristic algorithms. The algorithm has strong capability in the global search and local optimization.
The improved optimization algorithm is mainly divided into two types: one is to improve the core formula of the optimization algorithm by using the strategy method; the other is to combine the two optimization algorithms. The strategies commonly used by scholars are as follows opposition-based learning [
46], Levy-flight [
47], Gaussian mutation [
48], and so on. Opposition-based learning (OBL) as a new scheme for machine intelligence was introduced by Tizhoosh H R [
49]. The foundation of this new approach were estimates and counter-estimates, weights and opposite weights, and actions versus contraction. Trivedi I N used Levy flight improve the Moth-Flame optimization (MFO) [
50]. Results showed that applying MFO-LF yielded better facility locations compared other existing algorithms. Chenhua X U proposed an improved gray wolf optimization algorithm applied to solve the function optimization problem. The Gaussian disturbance based the rules of survival of the fittest was given to the global optimum of each generation, thus the algorithm could effectively jump out of local minima [
51]. The strategy method can effectively improve part of the ability of the algorithm, while the hybrid algorithm can combine the advantages of two or even more methods, so as to better improve the optimization ability of the algorithm [
52,
53]. Hybrid optimization algorithms are mainly divided into two types. One is to use a mechanism to select one of the two optimization algorithms for optimization, and use the two algorithms alternately in the iterative process for optimization. The other algorithm used the core formula of one algorithm to improve the other algorithm, and the optimizing ability obtained by different improved positions was also different. Guangqian, D. proposed a hybrid harmony search-simulated annealing method that combines the advantages of each one of the above-mentioned metaheuristic algorithms [
54]. The algorithm integrated the position updating formulas of the two optimization algorithms, and selected different position updating formulas for optimization with a certain mechanism, so as to apply to the hybrid wind/photovoltaic/biodiesel/battery system. Alsaeedan proposed hybrid algorithms for WSD that consist of a self-adaptive genetic algorithm (SAGA) and variants of ant colony optimization (ACO) algorithms: max-minant system (MMAS) and ant colony system (ACS) [
55]. Aziz M A E examined the ability of two nature inspired algorithms namely: whale optimization algorithm (WOA) and moth-flame optimization (MFO) to determine the optimal multilevel thresholding for image segmentation [
56]. The algorithm randomly selected an algorithm for optimization to solve the problem of multi-threshold image segmentation. Karishma Singh proposed a congestion control algorithm based on the multi-objective optimization algorithm named PSOGSA for route optimization and regulating the arrival rate of data from every child node to the parent node [
57]. Daniel E proposed an optimum Laplacian wavelet mask (OLWM) based fusion using hybrid cuckoo search-gray wolf optimization (HCS-GWO) for multimodal medical image fusion [
58]. This algorithm fully integrated the advantages of the two optimization algorithms, so as to solve the multi-objective problem. Orhan E proposed an effective new hybrid ant colony algorithm based on crossover and mutation mechanism for no-wait flow shop scheduling with the criterion to minimize the maximum completion time [
59]. Garg presented a hybrid technique named as a PSO-GA for solving the constrained optimization problems [
60]. This algorithm combined the advantages of the two optimization algorithms and proposed a new iterative updating formula. According to the above analysis, hybrid optimization algorithm can better use the advantages of different optimization algorithms to solve the various optimization problem.
In this paper, a 3DPCNN image segmentation algorithm based on HSOA is proposed to solve the complex problem of oil pollution image segmentation. Since the traditional 3DPCNN model has a general effect on oil pollution image segmentation, we use the optimization algorithm to optimize 3DPCNN parameters and improve the segmentation accuracy of the 3DPCNN model, so as to better obtain the oil polluted area in the image. We choose a hybrid optimization algorithm to achieve a balance between exploitation and exploration by taking advantage of SOA and TEO algorithm. In the HSOA algorithm, we improve the TEO algorithm’s heat exchange formula to the seagull attack formula in the SOA algorithm, so as to increase the exploitation of the SOA algorithm.
5. Oil Pollution Images Experiments and Results
In this experiment, for further showing the merits of 3DPCNN-HSOA method, the comparison is performed with other classical image segmentation algorithms, such as A Level Set Approach (LSA) [
74], multilevel thresholding (MS) [
75] and the optimal Color Image Multilevel Thresholding Technique (GLCM) [
76]. The images of the experiment are taken by a drone in the field, such as the
Figure 16. As can be seen from
Figure 16, (a) and (b) show that the oil pollution area is relatively obvious, while the oil pollution area of (c) and (d) has large interference, which brings great difficulties to the segmentation algorithm and can better verify the segmentation ability of the algorithm. This section uses an extensive comparative study on oil pollution by using performance metrics like Probability Rand Index (PRI), Variation of Information (VoI), Global Consistency Error (GCE), and Boundary Displacement Error (BDE) [
77,
78].
Table 6 shows the average results of PRI, BDE, GCE, and VoI of the oil pollution images.
Figure 17,
Figure 18,
Figure 19 and
Figure 20 shows the image segmentation results of each algorithm. Since there is no clear index for the oil pollution area actually photographed, we use Photoshop (PS) to segment the oil pollution area in the original image and take the segmentation result as the ground truth for comparison, and the subsequent indexes will be calculated according to the ground truth figure. As can be seen from the figure, 3DPCNN-HSOA can effectively segment the oil pollution area from the complex background. The LSA algorithm has a better effect on the oil pollution image with a simple background, as shown in
Figure 17b and
Figure 18b, but
Figure 17b has an over-segmentation phenomenon, and the redundant area is divided. When the LSA algorithm is used to segment complex images, the oil pollution area cannot be obtained and the segmentation effect is the worst, as shown in
Figure 19b and
Figure 20b. The segmentation results of MS and GLCM algorithm are similar, but it can be seen from
Figure 19 and
Figure 20 that the segmentation results of GLCM are better than that of MS, and the oil pollution area is more obvious. At the same time, the oil pollution boundary of MS is relatively fuzzy.
From the visual analysis and data results of the image segmentation results of oil pollution, it can be seen that the 3DPCNN-HSOA algorithm has a good ability for the image segmentation of oil pollution, and its time is relatively short.
The results displayed in
Table 6, that the proposed technique outperforms all other compared image segmentation algorithms. It can be seen from the table that the numerical value of 3DPCNN-HSOA algorithm is the best, indicating that the segmentation effect is the best. And the MS model segmentation effect is the most check. LSA and GLCM segmentation effect is not much different. The CPU running time of 3DPCNN-HSOA algorithm is the shortest, followed by GLCM and MS, and the running time of LSA algorithm is the slowest. According to the comparison between the results of image segmentation algorithms, the segmentation accuracy of 3DPCNN-HSOA algorithm is higher and its stability is better than other comparison algorithms. Therefore, the algorithm proposed in this paper has strong robustness, can complete the complex image segmentation task in a relatively short CPU time, and obtain good segmentation results with excellent segmentation accuracy.
6. Discussion
Oil pollution brings great damage to the environment. Oil leakage includes Oil spill and oil and gas drilling. The offshore oil spill has a large area of pollution and a long time of damage, and some damages are irreversible. Oil and gas drilling is widespread, oil is used in major equipment, the area of its contaminated continent is not easy to find, and the underground pipeline is complex, the damage caused by oil leakage should not be underestimated.
In this paper, unmanned aerial vehicles are used to take pictures of oil leakage in oil and gas drilling and ground pipelines. As the situation on the ground is relatively complex, and some buildings and number of buildings are shaded, the segmentation of the collected images poses a great challenge. The fast detection of oil spill method (FD) [
79] can detect offshore oil spills and identify vessels that have dumped oil. On the surface of the sea, the background is single and the oil target is obvious. The f-divergence minimization (FDM) [
80] can recognize oil spill images with different shapes. This method effectively reduces a large number of labeled data for neural network training. The one dot fuzzy initialization method (ODFI) [
81] that the fuzzy connecting between any initial point and the remaining pixels leads to a physically uniform region which is consistent with the minimization of the initial energy. This method can obtain relatively complete oil spill area. The above methods have a good effect on the segmentation of oil spill images, but they also have different disadvantages. FDM and ODFI require training data sets, and only by completing the training of neural network can the segmentation and identification of oil spill be realized. The FD algorithm is simple and easy to implement, but its ability to deal with complex background image segmentation is weak.
Figure 21 is the result of the PRI, BDE, GCE, VoI, and CPU time of each comparison algorithm. As can be seen from the figure, 3DPCNN-HSOA algorithm has the shortest running time and the highest segmentation accuracy. The FD has poor accuracy, but short operation time, the FDM and ODFI have a good segmentation accuracy, but long operation time. Therefore, 3DPCNN-HSOA algorithm has a good segmentation effect and excellent ability to solve the problem of oil and gas drilling oil leakage and pipeline oil leakage.
Because the ground background is complex and there are many buildings and trees, the algorithm is easy to divide the background of the building into oil pollution areas. The algorithm proposed in this paper has a good ability to segment simple background, as shown in the oil pollution image in
Figure 16d, with few tree shadows. The 3DPCNN-HSOA model can best obtain the oil pollution area. However, when the shadow area of trees is large, it is easy to divide the shadow into the dirty oil area. In the future research, we will focus on this problem to improve the segmentation ability of the algorithm and enhance the optimizing ability of the optimization algorithm. At the same time, we will study infrared and satellite image segmentation, to better solve the over-segmentation phenomenon.