Search

Due to the severe distortion of the fisheye image, the rectangular bounding box contain a lot of invalid information. So the multi-point representation method are emerging. However, it will fail in some extreme cases especially when the center of the object is not in the instance. In this work, we propose a Convex Hull Regression Strategy for people detection on top-view fisheye images. It replaces the instance with its convex hull to solve the above challenging issue and can be pre-trained on regular datasets without additional processing. In addition, the mosaic and mixup data augmentation methods that perform well under rectangular boxes are applied to our representation. Finally, we improve the label assignment and propose a more reasonable loss function called PDIoU loss so as to focus on the overall IoU between ground truth polygon and predicted polygon. Experimental results demonstrate that our method outperforms state-of-the-art algorithms. Source code is available at https://github.com/xiaoxuebajie/CHRS. [ABSTRACT FROM AUTHOR]

The civil aviation transportation has sustained rapid growth, which poses significant challenges in ensuring airport safety and efficiency of use. Persons and vehicles are tiny targets in airport surveillance. Existing detection methods are difficult to detect accurately. Enhancing small target detection by only the method of adding enhancement modules inevitably leads to increased network parameters. To address the above issues, this article proposes a lightweight airport surveillance detection based on YOLOv7 named LAS-YOLO. Firstly, we design the lightweight basic module, which significantly reduces network parameters while retaining certain local features. Secondly, we replace the SPPCSPC module with the spatial pyramid pooling-fast module with fewer parameters, further reducing the quantity of network parameters. Finally, the attention mechanism and small object detection layer are introduced to enhance small object detection accuracy. The efficient channel attention module is selected among three attention methods by experiments. We simulate the application process of object detection methods in airport surveillance, training on high-performance computers and testing on lower-performance computer. This article verifies the performance of the proposed method on the public ASS dataset consisting of the airport surface surveillance dataset (ASS1) and panoramic surveillance dataset (ASS2). The experiment shows that the parameters of LAS-YOLO are 12.5 M, which is 34.2 % of the original model. The mean average precision is 89.8 % on the ASS1. This proposed method enhances the average precision for airplane and vehicle detection by 14.5 % and 22.7 % compared to YOLOv7 on the ASS2. In order to reflect the robustness of the model in airport surveillance, we conduct another experiment using airplane data from the ROSD. The experiment demonstrates the superiority of the proposed method over other models in airport surveillance. Code is available at https://zenodo.org/records/10969930. [ABSTRACT FROM AUTHOR]

Autonomous decision-making in unmanned aerial vehicle (UVA) confrontations presents challenges in making optimal strategy. Therefore, deep reinforcement learning (DRL) has been adopted to address these issues. However, existing DRL decision-making models suffer from poor situational awareness and inability to distinguish between different intentions. Therefore, a multi-intent autonomous decision-making is proposed in this paper. First, three typical intentions are designed comprising head-on attacking, pursuing and fleeing to derive decision models representing different intentions. Reinforcement learning based air combat game model is constructed with different intentions, which contains designing reward functions for intentions to deal with the problem of sparse rewards. Then, we propose the Temporal Proximal Policy Optimization (T-PPO) algorithm, which optimizes the Proximal Policy Optimization algorithm by integrating the long short-term memory network and feedforward neural network. This algorithm extracts the historical temporal information to enhance situational awareness. In addition, a basic-confrontation progressive training method is proposed to provide intention guidance and increase training diversity, which can improve learning efficiency and intelligent decision-making capability. Finally, experiments in our constructed UAV confrontation environment demonstrate that the proposed intentional decision models exhibit good performance in stability and learning efficiency, achieving high rewards, win rates, and low steps. Specifically, our autonomous decision-making increases win rate by 26% when head-on attacking and learning efficiency by 50% when pursuing. It is further proof of the potential and value of our multi-intent autonomous decision-making applications. [ABSTRACT FROM AUTHOR]

The use of ammonia as a hydrogen vector has the potential to unlock the hydrogen economy. In this context, this paper presents novel insights into improving the ammonia decomposition activity of ruthenium nanoparticles supported on carbon nanotubes (CNT) by nitrogen doping. Our results can be applied to develop more active systems capable of delivering hydrogen on demand, with a view to move towards the low temperature target of less than 150 °C. Herein we demonstrate that nitrogen doping of the CNT support enhances the activity of ruthenium nanoparticles for the low temperature ammonia decomposition with turnover frequency numbers at 400 °C of 6200 LH mol h, higher than the corresponding value of unmodified CNT supports under the same conditions (4400 LH mol h), despite presenting similar ruthenium particle sizes. However, when the nitrogen doping process is carried out with cetyltrimethylammonium bromide (CTAB) to enhance the dispersion of CNTs, the catalyst becomes virtually inactive despite the small ruthenium particle size, likely due to interference of CTAB, weakening the metal-support interaction. Our results demonstrate that the low temperature ammonia decomposition activity of ruthenium can be enhanced by nitrogen doping of the CNT support due to simultaneously increasing the support's conductivity and basicity, electronically modifying the ruthenium active sites and promoting a strong metal-support interaction. [ABSTRACT FROM AUTHOR]

A Minimizing Intermediate Multicast Routing protocol (MIMR) is proposed for dynamic multi-hop ad hoc networks. In MIMR, multicast sessions are created and released only by source nodes. In each multicast session process, the source node keeps a list of intermediate nodes and destinations, which is encapsulated into the packet header when the source node sends a multicast packet. Nodes receiving multicast packets decide to accept or forward the packet according to the list. Depending on topology matrix maintained by unicast routing, the shortest virtual hierarchy routing tree is constructed by improved Dijkstra algorithm. MIMR can achieve the minimum number of intermediate nodes, which are computed through the tree. No control packet is transmitted in the process of multicast session. Load of the network is largely decreased. Experimental result shows that MIMR is flexible and robust for dynamic ad hoc networks. [ABSTRACT FROM AUTHOR]

Platinum and ruthenium nanoparticles stabilised by an amine modified polymer immobilised ionic liquid (MNP@NH2-PEGPIILS, M = Pt, Ru) catalyse the hydrolytic liberation of hydrogen from dimethylamine borane (DMAB), ammonia borane (AB) and NaBH4 under mild conditions. While RuNP@NH2-PEGPIILS and PtNP@NH2-PEGPIILS catalyse the hydrolytic evolution of hydrogen from NaBH4 with comparable initial TOFs of 6,250 molesH2.molcat−1.h−1 and 5,900 molesH2.molcat−1.h−1, respectively, based on the total metal content, RuNP@NH2-PEGPIILS is a markedly more efficient catalyst for the dehydrogenation of DMAB and AB than its platinum counterpart, as RuNP@NH2-PEGPIILS gave initial TOFs of 8,300 molesH2.molcat−1.h−1 and 21,200 molesH2.molcat−1.h−1, respectively, compared with 3,050 molesH2.molcat−1.h−1 and 8,500 molesH2.molcat−1.h−1, respectively, for PtNP@NH2-PEGPIILS. Gratifyingly, for each substrate tested RuNP@NH2-PEGPIILS and PtNP@NH2-PEGPIILS were markedly more active than commercial 5wt % Ru/C and 5wt% Pt/C, respectively. The apparent activation energies of 55.7 kJ mol−1 and 27.9 kJ mol−1 for the catalytic hydrolysis of DMAB and AB, respectively, with RuNP@NH2-PEGPIILS are significantly lower than the respective activation energies of 74.6 kJ mol−1 and 35.7 kJ mol−1 for its platinum counterpart, commensurate with the markedly higher initial rates obtained with the RuNPs. In comparison, the apparent activation energies of 44.1 kJ mol−1 and 46.5 kJ mol−1, for the hydrolysis NaBH4 reflect the similar initial TOFs obtained for both catalysts. The difference in apparent activation energies for the hydrolysis of DMAB compared with AB also reflect the higher rates of hydrolysis for the latter. Stability and reuse studies revealed that RuNP@NH2-PEGPIILS recycled efficiently as high conversions for the hydrolysis of DMAB were maintained across five runs with the catalyst retaining 97% of its activity.Graphical Abstract: Platinum and ruthenium nanoparticles stabilised by an amine modified polymer immobilised ionic liquid (MNP@NH2-PEGPIILS, M = Pt, Ru) catalyse the hydrolytic liberation of hydrogen from dimethylamine borane (DMAB), ammonia borane (AB) and NaBH4 under mild conditions. While RuNP@NH2-PEGPIILS and PtNP@NH2-PEGPIILS catalyse the hydrolytic evolution of hydrogen from NaBH4 with comparable initial TOFs of 6,250 molesH2.molcat−1.h−1 and 5,900 molesH2.molcat−1.h−1, respectively, based on the total metal content, RuNP@NH2-PEGPIILS is a markedly more efficient catalyst for the dehydrogenation of DMAB and AB than its platinum counterpart, as RuNP@NH2-PEGPIILS gave initial TOFs of 8,300 molesH2.molcat−1.h−1 and 21,200 molesH2.molcat−1.h−1, respectively, compared with 3,050 molesH2.molcat−1.h−1 and 8,500 molesH2.molcat−1.h−1, respectively, for PtNP@NH2-PEGPIILS. Gratifyingly, for each substrate tested RuNP@NH2-PEGPIILS and PtNP@NH2-PEGPIILS were markedly more active than commercial 5wt % Ru/C and 5wt% Pt/C, respectively. The apparent activation energies of 55.7 kJ mol−1 and 27.9 kJ mol−1 for the catalytic hydrolysis of DMAB and AB, respectively, with RuNP@NH2-PEGPIILS are significantly lower than the respective activation energies of 74.6 kJ mol−1 and 35.7 kJ mol−1 for its platinum counterpart, commensurate with the markedly higher initial rates obtained with the RuNPs. In comparison, the apparent activation energies of 44.1 kJ mol−1 and 46.5 kJ mol−1, for the hydrolysis NaBH4 reflect the similar initial TOFs obtained for both catalysts. The difference in apparent activation energies for the hydrolysis of DMAB compared with AB also reflect the higher rates of hydrolysis for the latter. Stability and reuse studies revealed that RuNP@NH2-PEGPIILS recycled efficiently as high conversions for the hydrolysis of DMAB were maintained across five runs with the catalyst retaining 97% of its activity. [ABSTRACT FROM AUTHOR]

The UAVs captured targets are relatively small when compared with the ordinary surveillance cameras. Thus, a strong discriminative ability is required for aerial trackers to accurately locate small targets, especially in challenging scenes, including similar objects, occlusion and size change. Since most existing aerial trackers do not perform satisfactorily, in this paper, we design a tracker called TAP-GC that utilizes a weight-sharing deep CNN network to extract the multi-scale template and test features. We then construct a target-aware pooling module in the template branch, allowing the tracker to pay more attention to the target-related information. Thereafter, we directly fuse the template and test features through a transformer which is able to make full use of the global context, enabling the tracker to discriminate the target more accurately. Extensive experiments on well-known aerial tracking benchmarks, UAV123, UAV123@10fps and DTB70, show that our tracker outperforms a number of state-of-the-art trackers. In addition, when evaluating TAP-GC on OTB100, a tracking benchmark captured by ordinary cameras, it also achieves leading tracking performance. TAP-GC can achieve about 70 fps speed for real-time UAV tracking. [ABSTRACT FROM AUTHOR]