Recognition of occluded pedestrians from the driver's perspective for extending sight distance and ensuring driving safety at signal-free intersections

Urban intersections without traffic signals are prone to accidents involving motor vehicles and pedestrians.Utilizing computer vision technology to detect pedestrians crossing the street can effectively mitigate the occurrence of such accidents.Faced with the complex issue of pedestrian occlusion at signal-free intersections,this paper proposes a target detection model called Head feature And ENMS fusion Residual connection For CNN(HAERC).Specifically,the model includes a head feature module that detects occluded pedestrians by integrating their head features with the overall target.Additionally,to address the misselection caused by overlapping candidate boxes in two-stage target detection models,an Extended Non-Maximum Suppression classifier(ENMS)with expanded IoU thresholds is proposed.Finally,leveraging the CityPersons dataset and categorizing it into four classes based on occlusion levels(heavy,reasonable,partial,bare),the HAERC model is experimented on these classes and compared with baseline models.Experimental results demonstrate that HAERC achieves superior False Positives Per Image(FPPI)values of 46.64%,9.59%,9.43%,and 6.78%respectively for the four classes,outperforming all baseline models.The study concludes that the HAERC model effectively identifies occluded pedestrians in the complex environment of urban intersections without traffic signals,thereby enhancing safety for long-range driving at such intersections.

Optimization of digital multi-beamforming for space-based ADS-B using distributed cooperative coevolution with an adaptive grouping strategy

Space-based Automatic Dependent Surveillance-Broadcast(ADS-B)technology can eliminate the blind spots of terrestrial ADS-B systems because of its global coverage capability.However,the space-based ADS-B system faces new problems such as extremely low Signal-toNoise Ratio(SNR)and serious co-channel interference,which result in long update intervals.To minimize the position message update interval at an update probability of 95%with full coverage constraint,this paper presents an optimization model of digital multi-beamforming for space-based ADS-B.Then,a coevolution method DECCG_A&A is proposed to enhance the optimization efficiency by using an improved adaptive grouping strategy.The strategy is based on the locations of uncovered areas and the aircraft density under the coverage of each beam.Simulation results show that the update interval can be effectively controlled to be below 8 seconds compared with other existing methods,and DECCG_A&A is superior in convergence to the Genetic Algorithm(GA)as well as the coevolution algorithms using other grouping strategies.Overall,the proposed optimization model and method can significantly reduce the update interval,thus improving the surveillance performance of space-based ADS-B for air traffic control.

Robustness analysis metrics for worldwide airport network：A comprehensive study

Robustness of transportation networks is one of the major challenges of the 21 st century.This paper investigates the resilience of global air transportation from a complex network point of view,with focus on attacking strategies in the airport network,i.e.,to remove airports from the system and see what could affect the air traffic system from a passenger＇s perspective.Specifically,we identify commonalities and differences between several robustness measures and attacking strategies,proposing a novel notion of functional robustness：unaffected passengers with rerouting.We apply twelve attacking strategies to the worldwide airport network with three weights,and evaluate three robustness measures.We find that degree and Bonacich based attacks harm passenger weighted network most.Our evaluation is geared toward a unified view on air transportation network attack and serves as a foundation on how to develop effective mitigation strategies.

Hybrid Beamforming Design for Uplink mmWave Systems with a Predefined Low-Resolution Codebook

In millimeter wave(mmWave)systems,desirable spectral efficiency can be realized by the hybrid beamformer in which a large sized analog beamformer and a small sized baseband digital beamformer are cascade-connected together to reduce the system cost.However,most of works focus on the beamforming(or combining)method design with an impractical analog beamformer where the infinite-resolution phase shifts(PSs)are adopted.In this paper,a more practical hybrid beamformer with low-resolution PSs is considered and the hybrid receiver beamforming method under the multiuser uplink communication circumstance is studied.Since the system performance is mainly constrained by the interuser interference,we propose a novel two-stage hybrid receiver beamforming against the inter-user interference with comparable computational complexity than that of the recently presented method.Moreover,to enhance the performance of systems with many users,we propose a novel multiuser selection algorithm by exploiting the multiuser diversity gain.Finally,from the simulation results,we can verify the superiority of the proposed method over the comparing method in error probability and spectrum efficiency.