A
Adversarial variational Bayes (AVB),
13,
17Adversarially learned inference (ALI),
13,
19Amazon Mechanical Turk (AMT),
151Ambient light sensors,
249Anchor point relation (APR),
225Application programming interface (API),
246Architecture,
11,
20,
22,
25,
26,
29,
105,
106,
109,
110,
112,
117,
121,
209,
214–216,
220,
238,
241,
244,
249,
387,
388,
391,
392Artificial intelligence (AI),
240Artificial neural network (ANN),
71,
247Automated localization,
239Automatic guided vehicles (AGV),
251Automatic multimodal coding systems,
Autonomous driving (AD), ,
10,
102,
160,
202,
238,
244,
252,
260,
261,
384Autonomous mobile robots (AMR),
251,
262B
Benchmark datasets,
11,
49BigLittle architecture,
244Binary class probabilities,
368,
373Binary classification fusion,
368Bounding box (BB), ,
43,
80,
81,
85–87,
92,
93,
95,
96,
98,
102,
103,
112,
113,
115,
117,
118Broadcast GNSS signal,
219Building information modeling (BIM),
264Buildings,
key geometric features,
326Bundle adjustment (BA),
224C
Candidate architecture,
242Centralized architecture,
203,
204,
207–209,
212–215,
219–224,
227–229,
232–235,
240–247,
249,
250CEVA deep neural network (CDNN),
242Classification,
69,
77,
80–82,
91,
92,
95,
107,
225,
238,
241,
247,
253,
317,
321,
324,
344,
346–349,
354,
356,
358,
361,
363,
364,
367,
369,
370,
372,
375,
376,
387,
391fusion,
Classification scores (CS),
112,
115Classifier, ,
46,
47,
81,
82,
84,
85,
317,
322,
344–346,
351,
353,
367,
372CNNs,
11,
43–45,
47,
67,
81,
98,
106,
222,
253,
365Color,
image, ,
75,
136,
138,
139,
144,
146,
147,
149,
151,
152,
154Computation architectures,
202Computer aided design (CAD),
251Concatenation,
12,
13,
29,
104,
105,
111,
119,
120,
130,
353,
367Concatenation fusion scheme, ,
104Conditional adversarial networks,
146,
147Conditional random field (CRF),
344Conduct multitask learning,
117Connected components (CC),
323Constructive Solid Geometry (CSG),
330Convolutional,
layers,
30,
45,
46,
48,
55,
62,
69,
73,
75–77,
81,
83,
84,
110–113,
116–118,
147,
388neural networks,
3–6,
10,
42,
66–68,
70,
75,
79–81,
84,
92,
222,
253,
332,
346,
365Convolutional accelerators (CA),
246Cooperative fusion,
203,
204,
207–209,
212–215,
219–224,
227–229,
232–235,
240–247,
249,
250Credibilist decision fusion,
344Cross correlation function (CCF),
225Cumulative distribution functions (CDF),
315Cumulative matching characteristic (CMC),
151Cumulative weight brightness transfer function (CWBTF),
137Cyber physical systems (CPS),
262D
Data fusion,
44,
60,
212,
214,
215,
227,
229,
230,
233,
234,
252,
253,
259,
260,
344,
370Decentralized architecture,
203,
204,
207–209,
212–215,
219–224,
227–229,
232–235,
240–247,
249,
250Deconvolutional layer,
147Deep,
autoencoder architecture,
387convolutional neural networks architecture,
106learning, ,
42,
98,
222,
224,
236–238,
241,
245,
253,
266,
280,
281CNN framework,
Deep learning accelerator (DLA),
245Depth,
image,
12,
36,
42,
43,
47,
48,
50,
51,
53,
56,
60,
61,
397measure,
Detection,
109,
118,
125,
128,
216,
259,
260,
263,
332,
333,
337,
343,
344,
364,
366,
372,
374Digital elevation model (DEM),
235,
258Digital signal processors (DSP),
242Digital surface models (DSM),
49,
50Direct memory access (DMA),
244Direct sparse odometry (DSO),
160,
165Discriminative features,
Discriminator network,
19,
147Drone,
163,
187,
189,
190,
200,
202,
212,
242,
247,
251,
256–258Dynamic vision sensor (DVS),
210E
Electronic control units (ECU),
261Encoder,
10,
13,
14,
18,
19,
24–27,
36,
44,
47,
48Evidential fusion rule,
345Expectation maximization (EM),
309Extended Kalman filter (EKF),
213,
228F
Feature,
maps, , ,
27,
76,
95,
104,
105,
110,
111,
113,
115–117,
119–121,
123,
130,
387,
390,
394,
396Floating Point Unit (FPU),
244Functional safety features,
244Fusion,
372model classification result,
356rules, ,
344,
345,
347–353,
358,
363,
372,
373,
376,
377G
Generative adversarial network (GAN), , ,
13,
15,
16,
19,
22,
24,
136,
138,
145,
147,
154,
236Geometrical features,
222,
234Global positioning system (GPS),
205GNSS, ,
201–203,
205,
216,
218,
220,
226,
232,
233,
235,
237,
249,
252,
265Graphic processing units (GPU),
242Ground sampling distance (GSD),
51Ground truth,
20,
28,
29,
32,
34,
56,
60–62,
91,
93,
96,
137,
187,
238,
254,
266,
347,
351,
353,
361,
363,
364,
367,
369,
370,
372,
374–377H
Hallucinated feature maps,
387,
393Hallucination,
network learning process,
396Handcrafted features,
387Heterogeneous sensor data fusion,
212,
216Heterogeneous sensor fusion,
239Hierarchical architectures,
203,
204,
207–209,
212–215,
219–224,
227–229,
232–235,
240–247,
249,
250High dynamic range (HDR),
244High performance computer (HPC),
246Holographic processing unit (HPU),
250I
Image signal processors (ISP),
242Independent classifiers,
344Indian regional navigation satellite system (IRNSS),
206Indoor,
images semantic segmentation,
62pedestrian navigation,
232semantic segmentation,
49Inertial data fusion,
230Inertial measurement unit (IMU), , ,
160,
203Inertial navigation system (INS),
201Inertial sensors, ,
203,
204,
207–209,
212–215,
219–224,
227–229,
232–235,
240–247,
249,
250,
259Infrared sensors,
Insufficient training data,
80Integrate channel features (ICF),
106Integrated circuit (IC),
209Intellectual property (IP),
241ISPRS Vaihingen dataset,
58,
60Iterative dual correspondence (IDC),
225J
Joint multitask training,
12K
L
Laser imaging detection,
201Layer,
45,
46,
71–73,
75–77,
83,
84,
110,
116,
333,
335,
336,
387,
388,
390,
391multimodal feature fusion,
110Layer for classification,
106Learning, ,
13,
15,
67,
68,
75,
125,
130,
235,
238,
247,
253,
266,
281–283,
285,
385,
392,
393,
396,
399deep, ,
42,
98,
222,
224,
236–238,
241,
245,
253,
266,
280,
281package,
Least class confusions,
372LiDAR, ,
42,
201,
211–213,
218,
225,
226,
231,
234,
235,
237,
252,
262,
265,
342,
344,
345Local steering kernel (LSK),
108Localization,
203,
204,
207–209,
212–215,
219–224,
227–229,
232–235,
240–247,
249,
250multimodal, ,
202,
218,
221,
226,
227,
231,
237,
239,
248,
255,
259,
261,
265,
266Localizing ground penetrating radar (LGPR),
255Long term evolution (LTE),
249Loss,
function,
26,
28,
74,
75,
147,
385,
386,
391,
392,
395Loss term,
113for scene prediction,
123segmentation supervision,
117M
Machine learning, ,
66,
67,
221,
222,
243,
246,
247,
256,
280Machine learning performance,
243Markov random fields (MRF),
347Maximally stable color regions (MSCR),
148Maximally stable extremal region (MSER),
148,
221Mean intersection over union (MIOU),
30Micro aerial vehicle (MAV),
160Mobile industry processor interface (MIPI),
245Modalities, ,
10,
12,
26,
29,
235,
237,
238,
251,
265,
384–386,
388,
390,
393,
394,
396,
398Model,
spatiotemporal features,
387Monocular video camera,
233Monomodal localization,
218Multicore architecture,
246Multilayer perceptrons,
72Multimodal,
deep learning techniques,
11feature,
fusion architectures,
fusion architectures,
105localization, ,
202,
218,
221,
226,
227,
231,
237,
239,
248,
255,
259,
261,
265,
266pedestrian,
117,
118,
120,
124detectors performance,
122detectors quantitative performance,
118retrieval,
scene understanding, ,
segmentation supervision,
116,
124infusion architectures,
104semantic segmentation,
thermal image generation,
150Multiple,
multispectral datasets,
138Multipurpose applications,
230Multiscale discriminator architecture,
21Multispectral,
pedestrian detection performance,
semantic segmentation,
154ThermalWorld dataset,
137,
154N
Network,
in semantic segmentation,
42interface communication tasks,
241Neural networks, ,
12,
13,
20,
42,
48,
51,
67–73,
75,
81,
82,
84,
91,
98,
242,
244,
286convolutional,
3–6,
10,
42,
66–68,
70,
75,
79–81,
84,
92,
222,
253,
332,
346,
365Neural processing unit (NPU),
242Next generation mobile network (NGMN),
217Nighttime segmentation prediction,
117O
Object detection, , ,
11,
44,
67,
79,
91,
92,
98,
106,
222,
236,
384,
400Optimal,
segmentation fusion scheme,
125Optimum performances,
286P
Particular filter (PF),
229Performance,
multimodal pedestrian detection,
119,
124,
125pedestrian detection,
106segmentation supervision,
117,
125Photometric camera parameters,
167Pixelwise classification,
333Pose,
203,
204,
207–209,
212–215,
219–224,
227–229,
232–235,
240–247,
249,
250estimation, ,
182,
192,
221,
225,
246,
256,
263,
308–310,
312–314,
337regression,
203,
204,
207–209,
212–215,
219–224,
227–229,
231–235,
240–247,
249,
250Posterior class probabilities,
348,
358Potential relocalization,
263Powerful computing architecture,
266Probabilistic autoencoder,
17Professional mapping drone,
257Programmable vision accelerators (PVA),
244Pseudo random code (PRC),
206Q
Quadratic entropy (QE),
349R
Random forest, , ,
67–69,
73,
75–77,
79,
81–84,
91,
92,
95,
98,
317,
343,
345,
346,
353,
358,
365,
367Random forest classification,
82,
92Region proposal network (RPN),
112Remote sensing,
1–3, ,
44,
45,
47,
49,
62,
342,
344,
364Remote sensing modalities,
RGB,
image generation from depth,
28Root mean square error (RMSE),
187S
Satisfactory accuracy,
363Scene prediction network (SPN),
113,
121Segmentation,
11,
12,
42,
47,
116,
117,
125,
141,
147,
344,
347masks supervision learning,
103semantic, , ,
10–12,
26,
27,
29–33,
41,
42,
81,
109,
116Semantic,
information, , ,
105,
203,
204,
207–209,
212–215,
219–224,
227–229,
231–235,
240–247,
249,
250segmentation, , ,
10–12,
26,
27,
29–33,
41,
42,
81,
109,
116Sensors,
fusion architectures,
214Shape distribution histogram (SDH),
107Siamese network structures,
48Simultaneous location and mapping (SLAM), ,
201,
243Smart,
phone,
66–68,
89,
90,
97,
205,
218,
220,
241–243,
248,
249,
253,
254,
259,
260phone localization application,
254Software Development Kit (SDK),
249Standard dynamic random access memory (SDRAM),
245Static random access memory (SRAM),
246Stereo camera sensor,
251Stereo thermal images,
107Stochastic gradient descent (SGD),
18,
55Supervision, ,
23,
24,
105,
109,
116,
117,
124,
130,
386Supervision information,
106Support Vector Machine (SVM),
353,
367SVM supervised fusions,
372T
Teacher learning phase,
393Text embeddings, ,
281,
283–286,
289,
293,
294,
298,
299,
302,
304Thermal,
images,
107,
108,
121,
122,
136,
138,
139,
142,
144,
145,
148,
149,
151–153U
Underwater localization purposes,
233Unmanned aerial vehicles (UAV), ,
202,
233Unmanned ground vehicle (UGV),
237Unmatched detections,
118Unscented Kalman filter (UKF),
213,
229Unscented transform (UT),
229Unsupervised,
feature learning methods,
80Urban,
land cover classification,
343,
357scene classification,
317scene reconstruction, ,
337V
Vehicle localization,
226Video classification,
390Video graphics array (VGA),
210Vision processing unit (VPU),
246W
Weighted parallel iterative closed point (WPICP),
226Wide video graphics array (WVGA),
231WiFi communication networks,
216Window classification,
107