Embedded Night-Vision System for Pedestrian Detection

Nowosielski, Adam; Małecki, Krzysztof; Forczmański, Paweł; Smoliński, Anton; Krzywicki, Kazimierz

doi:10.1109/jsen.2020.2986855

Cited by 29 publications

(25 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The IoU (Intersection over Union) for object detection [14,15] has been adopted for testing the clustering effect, thus avoiding the error caused by the box scale. The distance (D) function is where the box is the sample; the centroid is a center point of the cluster; IoU is the cluster box's overlap ratio and the center box.…”

Section: Yolo Algorithmmentioning

confidence: 99%

“…Therefore, there have been great efforts to design state-of-the-art methods based on deep learning approaches that are typically used in object detectors [5,[8][9][10][11][12][13][14]. These approaches indicated that to detect objects with high-precision definition features [15]. However, it is still challenging to classify images that contain more than one object [16].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Real-time human detection in thermal infrared imaging at night using enhanced Tiny-yolov3 network

Manssor

Sun

Abdalmajed

et al. 2021

J Real-Time Image Proc

View full text Add to dashboard Cite

Human detection is a technology that detects human shapes in the image and ignores everything else. However, modern person detectors have some inefficiencies in detecting pedestrians during video surveillance at night, and the accuracy rate is still insufficient. Therefore, this paper aims to increase the accuracy rate for automatic human detection at night from thermal infrared (TIR) images and real-time video sequences. For this purpose, a new architecture is proposed to enhance the backbone of the Tiny-yolov3 network. The enhanced network used the YOLOv3 algorithm's tasks with the K-means clustering method to extract more complex features of a person. This network was pre-trained on the MS. COCO dataset to obtain the initial weights. Through the comparison with other related methods showed that the experimental results have achieved the significantly improved performance of human detection from thermal imaging in terms of accuracy, speed, and detection time. The method has achieved a high accuracy rate (90%) compared with the TF-YOLOv3 (88%) trained on the DHU Night Dataset. Although the method has achieved an accuracy rate equal to the YOLOv3-Human (90%), the detection time (4.88 ms) is less, Furthermore, the method has a higher accuracy rate (49.8%) than the YOLO (29.36%) and TF-YOLOv3 (29.8%) with lower detection time (8 ms) on the FLIR Dataset. In addition, the model has achieved a good TP detection for multiple small size of person. By improving the performance of human detection in thermal imaging at night, the method will be able to detect intruders in the night surveillance system.

show abstract

Section: Yolo Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Real-time human detection in thermal infrared imaging at night using enhanced Tiny-yolov3 network

Manssor

Sun

Abdalmajed

et al. 2021

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…This idea was introduced in the middle of the twentieth century but needed a long time to turn it into reality, which was possible thanks to the increase in computation power and galloping miniaturisation. Currently, there are numerous applications of AI, including autonomous vehicles, cybersecurity, biometrics and many others (Choraś et al, 2019 ; Nowosielski et al, 2020 ; Orrù et al, 2020 ).…”

Section: Introduction To Digitalisation and Artificial Intelligencementioning

confidence: 99%

Deploying digitalisation and artificial intelligence in sustainable development research

Filho

Yang

Eustachio

et al. 2022

Environ Dev Sustain

View full text Add to dashboard Cite

Many industrialised countries have benefited from the advent of twenty-first century technologies, especially automation, that have fundamentally changed manufacturing and industrial production processes. The next step in the evolution of automation is the development of artificial intelligence (AI), i.e. intelligence which is demonstrated by machines and systems, which cannot only perform tasks but also work synergistically with humans and nature. Intelligent systems that can see, analyse situations and respond sensitively to real-time cues, from human gestures and facial expressions to pedestrians crossing a busy street, will reshape transportation, precision agriculture, biodiversity conservation, environmental modelling, public health, construction and manufacturing, as well as initiatives designed to promote prosperity on Earth. This paper explores the connections between AI systems and sustainable development (SD) research. By means of a literature review, world survey, and case studies, ways in which AI can support research on SD and, inter alia, contribute to a more sustainable and equitable world, are identified.

show abstract

“…Many researchers have studied the critical factors in crash severity [5][6][7][8] and some focused on the effect of lighting conditions on crash severity [9][10][11][12][13][14][15][16]. Table 1 illustrates a selection of research conducted in this field, making it clear that lighting conditions influence injury severity.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Crash Severity of Texas Two Lane Rural Roads Using Solar Altitude Angle Based Lighting Condition

et al. 2022

View full text Add to dashboard Cite

Many studies have examined the impact of factors affecting accident severity in rural areas; however, little attention has been paid to different lighting conditions (LCs), and less to the detailed categories and precise determining of twilight. In this paper, solar altitude angle (SAA), as a basis for differentiating and categorizing LCs, is proposed to investigate explanatory variables in much greater detail. For each LC, namely, dark, twilight, dark lit (dark with street lights) and daylight, separate random parameter models are developed to investigate the impacts of some factors on crash injury severity data of 2017 and 2018 in two lane rural roads of Texas. The model estimation results indicated that different LCs have various contributing factors, indeed, to each injury severity, further stressing the significance of investigating crashes based on SAA. The key differences include crash location, marked lane, grade direction, no passing zone, shoulder width, weekday and collision type. The important findings were that developing artificial lighting at intersections and LED raised pavement markers on two lane rural roads could lead to enhanced road safety under dark LCs. Furthermore, increasing shoulder width in straight segments of two lane rural roads is important for decreasing severe injury in daylight conditions.

show abstract

Embedded Night-Vision System for Pedestrian Detection

Cited by 29 publications

References 51 publications

Real-time human detection in thermal infrared imaging at night using enhanced Tiny-yolov3 network

Real-time human detection in thermal infrared imaging at night using enhanced Tiny-yolov3 network

Deploying digitalisation and artificial intelligence in sustainable development research

Analysis of Crash Severity of Texas Two Lane Rural Roads Using Solar Altitude Angle Based Lighting Condition

Contact Info

Product

Resources

About