TY - GEN
T1 - In-vehicle object detection in the wild for driverless vehicles
AU - Dinakaran, Ranjith
AU - Zhang, Li
AU - Jiang, Richard
PY - 2020/9/1
Y1 - 2020/9/1
N2 - In-vehicle human object identification plays an important role in vision-based automated vehicle driving systems while objects such as pedestrians and vehicles on roads or streets are the primary targets to protect from driverless vehicles. A challenge is the difficulty to detect objects in moving under the wild conditions, while illumination and image quality could drastically vary. In this work, to address this challenge, we exploit Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) to handle with the wild conditions. In our work, a GAN was trained with low-quality images to handle with the challenges arising from the wild conditions in smart cities, while a cascaded SSD is employed as the object detector to perform with the GAN. We used tested our approach under wild conditions using taxi driver videos on London street in both daylight and night times, and the tests from in-vehicle videos demonstrate that this strategy can drastically achieve a better detection rate under the wild conditions.
AB - In-vehicle human object identification plays an important role in vision-based automated vehicle driving systems while objects such as pedestrians and vehicles on roads or streets are the primary targets to protect from driverless vehicles. A challenge is the difficulty to detect objects in moving under the wild conditions, while illumination and image quality could drastically vary. In this work, to address this challenge, we exploit Deep Convolutional Generative Adversarial Networks (DCGANs) with Single Shot Detector (SSD) to handle with the wild conditions. In our work, a GAN was trained with low-quality images to handle with the challenges arising from the wild conditions in smart cities, while a cascaded SSD is employed as the object detector to perform with the GAN. We used tested our approach under wild conditions using taxi driver videos on London street in both daylight and night times, and the tests from in-vehicle videos demonstrate that this strategy can drastically achieve a better detection rate under the wild conditions.
UR - https://www.worldscientific.com/doi/abs/10.1142/9789811223334_0136
U2 - 10.1142/9789811223334_0136
DO - 10.1142/9789811223334_0136
M3 - Conference contribution
SP - 1139
EP - 1147
BT - The 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020)
ER -