Recently, researchers have realized a number of achievements involving deep-learning-based neural networks for the tasks of segmentation and detection based on 2D images, 3D point clouds, etc. Using 2D and 3D information fusion for the advantages of compensation and accuracy improvement has become a hot research topic. However, there are no critical reviews focusing on the fusion strategies of 2D and 3D information integration based on various data for segmentation and detection, which are the basic tasks of computer vision. To boost the development of this research domain, the existing representative fusion strategies are collected, introduced, categorized, and summarized in this paper. In addition, the general structures of different kinds of fusion strategies were firstly abstracted and categorized, which may inspire researchers. Moreover, according to the methods included in this paper, the 2D information and 3D information of different methods come from various kinds of data. Furthermore, suitable datasets are introduced and comparatively summarized to support the relative research. Last but not least, we put forward some open challenges and promising directions for future research.

No abstract

Six polycyclic aromatic hydrocarbons (PAHs) including naphthalene (Nap), fluorene (Flu), phenanthrene (Phe), fluoranthene (Fla), pyrene (Pyr), and chrysene (Chr) were detected in runoff from five athletic fields during three rainfall events. The event mean concentration (EMC) of ∑6PAHs ranged from 3.96 to 23.23 μg/L, which was much higher than the EMC in urban traffic area runoff. Except for Nap, the PAH concentrations followed in the order of artificial turf > badminton court > basketball court > plastic runway > optennis court. The surface characteristics of the athletic fields, such as the composition of materials and roughness, played an essential role in the release of PAHs. ∑6PAHs concentration during the 2nd rainfall event (July 22nd) was the highest among the three rainfall events, indicating that high rainfall intensity facilitated the PAHs release. PAHs during three rainfall events showed little first flush effect except for the artificial turf during the 2nd (22nd July) and 3rd (29th July) rainfall events. The first flush effect could be affected by rainfall characters, PAH properties, and surface characteristics of athletic fields. Ecological risk assessment showed that PAHs in runoff corresponded to moderate-to-high risk, while health risk assessment showed that PAHs could pose a potential carcinogenic danger to human health via dermal contact.

Environmental risk of heavy metals and metalloids in athletic fields has raised people’s attention in the recent years. Seven trace elements, including metals and metalloids, were detected in the runoff of five typical athletic fields in the university campus under three rainfall events. Except for Cr, the total concentrations of Zn, Pb, Cu, Mn, Cd, and As in artificial turf runoff are the highest among five athletic fields, followed by that of plastic runway. The concentration and first flush effect of trace elements are followed in the order of 1st > 2nd > 3rd rainfall events. The strongest correlations between metals and metalloids were observed in the tennis court runoff, while the artificial turf shows the least. The release of trace elements could be directly from the surface materials and particles on the athletic field and influenced by the comprehensive factors including surface materials, rainfall events, and pollutant characters. Pollution risk assessment shows that the pollution extent of the five types of athletic field is at least “moderate” and follows the order of artificial turf > basketball court > plastic runway > badminton court > tennis court. Pb shows the highest pollution level, while Cr shows the highest healthy risk. The results can provide a theoretical basis for runoff pollution control and safety use of athletic fields.

Coal gangue (CG) as mineral waste was properly treated and applied as the filter media in permeable pavement systems due to its good sorption ability and mechanical strength. Batch experiments show the maximum adsorption capacity of calcined CG to phosphorus could reach 2.63 mg/g. To evaluate the removal effect of typical runoff pollutants including chemical oxygen demand (COD), total nitrogen (TN), total phosphorus (TP) and ammonia (NH4+-N), the gravel and sand in a traditional pavement system were replaced by CG respectively. The leaching behavior of the four pollutants in CG modified systems is limited and comparable with traditional system, indicating pretreated CG as filler would not cause environmental risk. CG-based pavement systems improved the removal efficiency of the four pollutants especially for TP. The removal mechanisms including interception, adsorption and microorganism degradation. The removal rates of COD, NH4+-N and TN by CG modified and traditional systems decreased with rainfall duration, while it is not obviously changed with rainfall recurrence period and drying period. Overall, the permeable pavement with CG layers that replaced both sand and gravel layers show best removal efficiency of all pollutants investigated especially for TP (>95%). This study provides a new way for CG utilization and gives the reference for the process design of permeable pavement.