IEEE Consumer Electronics Magazine - September/October 2022 - 53

proposed method predicts 2-D and 3-D bounding
boxes simultaneously around objects utilizing a
single internal network. Initially, a monocular RGB
image is passed as an input to the model, and the
feature maps are extracted through a strong backbone
deep learning model. These feature maps
are further processed by RPN to create proposals
utilizing 2-D and 3-D anchor boxes. Besides, nonmaximum
suppression is applied to suppress
redundant proposals. Experimental results on the
KITTI benchmark indicate that the performance of
the proposed method is much efficient for 3-D
object detection and localization as compared to
prior methods. Specifically, the proposed method
has improved the average precision of the car
class for localization and 3-D object detection
tasks up to 32% and 25%, respectively. For future
studies, more extensive experiments are expected
on the recent 3-Dobject detection benchmarks.
&REFERENCES
1. B. Markwalter, " The path to driverless cars [CTA
insights], " IEEEConsum. Electron. Mag., vol. 6, no. 2,
pp. 125-126, Apr. 2017.
2. J. Guerry, A. Boulch, B. L. Saux, J. Moras, A. Plyer,
and D. Filliat, " SnapNet-R: Consistent 3D multi-view
semantic labeling for robotics, " in Proc. IEEE Int. Conf.
Comput. Vis. Workshops, Oct. 2017, pp. 669-678.
3. V. K. Kukkala, J. Tunnell, S. Pasricha, and T. Bradley,
" Advanced driver-assistance systems: A path toward
autonomous vehicles, " IEEEConsum. Electron. Mag.,
vol. 7, no. 5, pp. 18-25, Sep. 2018.
4. A. Mousavian, D. Anguelov, J. Flynn, and J. Ko secka,
" 3D bounding box estimation using deep learning and
geometry, " in Proc. IEEEConf. Comput. Vis. Pattern
Recognit., Jul. 2017, pp. 5632-5640.
5. A. Simonelli, S. R. Bulo, L. Porzi, M. L. Antequera, and
P. Kontschieder, " Disentangling monocular 3D object
detection: From single to multi-class recognition, " IEEE
Trans. Pattern Anal. Mach. Intell., to be published,
2020, doi: 10.1109/TPAMI.2020.3025077.
6. G. Brazil and X. Liu, " M3D-RPN: Monocular 3D region
proposal network for object detection, " in Proc. IEEE/
CVFInt. Conf. Comput. Vis., Seoul, South Korea,
Oct. 2019, pp. 9286-9295.
7. X.Ma,S. Liu,Z. Xia, H.Zhang, X.Zeng,andW.Ouyang,
" Rethinking pseudo-LiDAR representation, " in Proc.
Comput. Vis. (ECCV), Cham, Switzerland, 2020,
pp. 311-327, doi: 10.1007/978-3-030-58601-0_19.
8. K.He, X. Zhang, S. Ren, and J. Sun, " Deep residual
learning for image recognition, " in Proc. IEEEConf.
Comput. Vis. PatternRecognit.,Jun.2016,pp. 770-778.
9. A. Geiger, P. Lenz, and R. Urtasun, " Are we ready for
autonomous driving? The KITTI vision benchmark
suite, " in Proc. IEEEConf. Comput. Vis. Pattern
Recognit., Jun. 2012, pp. 3354-3361.
10. X. Ma, Z. Wang, H. Li, P. Zhang, W. Ouyang, and
X. Fan, " Accurate monocular 3D object detection via
color-embedded 3D reconstruction for autonomous
driving, " in Proc. IEEE/CVFInt. Conf. Comput. Vis.,
Seoul, South Korea, Oct. 2019, pp. 6850-6859.
Qazi Mazhar ul Haq is currently working toward
the Ph.D. degree in electronic and computer engineering
with the National Taiwan University of Science
and Technology. His research interests include
object detection, classification, life-long learning,
and medical image processing. Contact him at
q.mazhar876@gmail.com.
Muhamad Amirul Haq is currently working toward
the Ph.D. degree in electronics and computer engineering
with the National Taiwan University of Science
and Technology, Taipei, Taiwan. His research interests
include object detection, classification, computer
vision, and display technology. Contact him at
amirul.haq@outlook.co.id.
Shanq-Jang Ruan is a Distinguished Professor
with the Department of Electronics and Computer
Engineering, National Taiwan University of Science
and Technology, Taipei, Taiwan. He received the
Ph.D. degree in electrical engineering from National
Taiwan University, Taipei, in 2002. His research interests
include embedded deep neural network processing
and image processing. Contact him at
sjruan@mail.ntust.edu.tw.
Pei-Jung Liang is currently an Engineer with Industrial
Technology Research Institute. Her research interests
include autonomous driving systems, robot
control, and artificial intelligence. Contact her at
pattyliang@itri.org.tw.
De-Qin Gao is currently an Engineer with Industrial
Technology Research Institute. His research interests
include machine learning, visual reasoning,
and natural language processing. Contact him at
charliegao@itri.org.tw.
September/October 2022
53
http://dx.doi.org/10.1109/TPAMI.2020.3025077 http://dx.doi.org/10.1007/978-3-030-58601-0_19
IEEE Consumer Electronics Magazine - September/October 2022

Table of Contents for the Digital Edition of IEEE Consumer Electronics Magazine - September/October 2022
