Occluded Pedestrian Classification Using Gradient Patch and Convolutional Neural Networks

Kim, Sangyoon; Kim, Moonhyun

doi:10.1007/978-981-10-3023-9_32

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A generative stochastic neural network model is used to estimate the posterior probability of pedestrian given its components scores. [5] uses Gradient Patch and a CNN to learn partial features and tackle occlusion without any prior knowledge. In [16] HOG features were used to create an occlusion likelihood map of the scanning window.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Occlusion aware sensor fusion for early crossing pedestrian detection

Palffy

Kooij

Gavrila

2019

2019 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Early and accurate detection of crossing pedestrians is crucial in automated driving to execute emergency manoeuvres in time. This is a challenging task in urban scenarios however, where people are often occluded (not visible) behind objects, e.g. other parked vehicles. In this paper, an occlusion aware multi-modal sensor fusion system is proposed to address scenarios with crossing pedestrians behind parked vehicles. Our proposed method adjusts the detection rate in different areas based on sensor visibility. We argue that using this occlusion information can help to evaluate the measurements. Our experiments on real world data show that fusing radar and stereo camera for such tasks is beneficial, and that including occlusion into the model helps to detect pedestrians earlier and more accurately.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Thus, a pedestrian detection system has two aims: early detection and accurate tracking of the VRU. Intelligent vehicles have several sensors to cope with this task: cameras [3], [4], [5], LIDARs, [6], and radars [7], [8], [9] have been used. Fusing different type of sensors, e.g.…”

Section: Introductionmentioning

confidence: 99%