Special Sessions - Revision history

Faber at 09:36, 29 June 2016

2016-06-29T09:36:41Z

Faber at 08:09, 6 June 2016

2016-06-06T08:09:15Z

Faber at 08:58, 23 May 2016

2016-05-23T08:58:10Z

Faber at 08:40, 23 May 2016

2016-05-23T08:40:27Z

Faber at 09:59, 17 May 2016

2016-05-17T09:59:20Z

Faber at 09:48, 17 May 2016

2016-05-17T09:48:21Z

Faber at 09:47, 17 May 2016

2016-05-17T09:47:18Z

Faber at 09:40, 17 May 2016

2016-05-17T09:40:11Z

Faber at 09:37, 17 May 2016

2016-05-17T09:37:18Z

Faber at 09:26, 1 April 2016

2016-04-01T09:26:09Z

@@ Line 242: / Line 242: @@
 | style="border:1px solid transparent;" |<br />
 |-
 __NOTOC____NOEDITSECTION__

@@ Line 34: / Line 34: @@
 * [[Special_Sessions#ss8| SS8 Multisensor Fusion Methods for Radiation Source Localization]]
 * [[Special_Sessions#ss9| SS9 Multiple (Extended) Object Tracking]]
 </div>
 |}
@@ Line 218: / Line 219: @@
 '''Organizers:''' [mailto:karl.granstrom@chalmers.se Karl Granström], [mailto:stephan.reuter@uni-ulm.de Stephan Reuter], [mailto:marcus.baum@cs.uni-goettingen.de Marcus Baum]
 |-

@@ Line 33: / Line 33: @@
 * [[Special_Sessions#ss7| SS7 Multi-Robot Systems and Mobile Sensor Networks]]
 * [[Special_Sessions#ss8| SS8 Multisensor Fusion Methods for Radiation Source Localization]]
 </div>
 |}
@@ Line 197: / Line 198: @@
 '''Organizers:''' [mailto:john_mattingly@ncsu.edu John Mattingly]
 |-

@@ Line 31: / Line 31: @@
 * [[Special_Sessions#ss5| SS5 Homotopy Methods in State Estimation]]
 * [[Special_Sessions#ss6| SS6 Data Fusion in Sensor-based Sorting]]
 </div>
 |}
@@ Line 157: / Line 159: @@
 '''Description:''' Sensor-based sorting is an established technology for sorting of various products according to quality aspects. Fields of application include food processing, recycling, and industrial mineral processing. Selection of a sensor suitable for material characterization typically depends on the product under inspection as well as the sorting task itself. However, in many cases increased sorting performance is achieved by combining information retrieved from multiple different sensors, for example line-scan and area-scan cameras, near-infrared cameras, X-ray, 3D sensors, or hyperspectral cameras. Hence, sensor data needs to be fused to increase performance by putting information in a temporal and / or spatial context. This applies for systems including several sensors of the same kind as well as heterogeneous combinations. Additionally, sensor-based sorting systems are typically restricted in terms of the time being available to derive a sorting decision. Therefore, real-time capable information fusion methods are required.
-'''Organizers:''' [mailto:georg.maier@iosb.fraunhofer.de Georg Maier],[mailto:Robin.Gruna@iosb.fraunhofer.de Robin Gruna]
+'''Organizers:''' [mailto:georg.maier@iosb.fraunhofer.de Georg Maier], [mailto:Robin.Gruna@iosb.fraunhofer.de Robin Gruna]
 |-

@@ Line 157: / Line 157: @@
 '''Description:''' Sensor-based sorting is an established technology for sorting of various products according to quality aspects. Fields of application include food processing, recycling, and industrial mineral processing. Selection of a sensor suitable for material characterization typically depends on the product under inspection as well as the sorting task itself. However, in many cases increased sorting performance is achieved by combining information retrieved from multiple different sensors, for example line-scan and area-scan cameras, near-infrared cameras, X-ray, 3D sensors, or hyperspectral cameras. Hence, sensor data needs to be fused to increase performance by putting information in a temporal and / or spatial context. This applies for systems including several sensors of the same kind as well as heterogeneous combinations. Additionally, sensor-based sorting systems are typically restricted in terms of the time being available to derive a sorting decision. Therefore, real-time capable information fusion methods are required.
-'''Organizers:''' [mailto:georg.maier@iosb.fraunhofer.de], [mailto:Robin.Gruna@iosb.fraunhofer.de Robin Gruna]
+'''Organizers:''' [mailto:georg.maier@iosb.fraunhofer.de Georg Maier],[mailto:Robin.Gruna@iosb.fraunhofer.de Robin Gruna]
 |-

@@ Line 146: / Line 146: @@
 | style="border:1px solid transparent;" |<br />
 |-
 <!--        MFI 2016 Accepted Special Sessions        -->
 {| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;"
 <div id="ss6"></div>
-<!--        SS6  Homotopy Methods in State Estimation         -->
+<!--        SS6  Text6        -->
-| class="MainPageBG" style="width:100%; border:1px solid #f2ea7e; background:#ffffe8; vertical-align:top; color:#000;" |
+| class="MainPageBG" style="width:100%; border:1px solid #d6bdde; background:#f7eff7; vertical-align:top; color:#000;" |
-{| id="mp-left" style="width:100%; vertical-align:top; background:#ffffe8;"
+{| id="mp-left" style="width:100%; vertical-align:top; background:#e7f7e76;"
-| style="padding:2px;" | <h2 id="mp-tfa-h2" style="margin:3px; background:#fff7bd; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #f2ea7e; text-align:left; color:#000; padding:0.2em 0.4em;">SS6 Data Fusion in Sensor-based Sorting</h2>
+| style="padding:2px;" | <h2 id="mp-tfa-h2" style="margin:4px; background:#e7deef; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #d6bdde; text-align:left; color:#000; padding:0.2em 0.4em;">SS6 Data Fusion in Sensor-based Sorting</h2>
 |-
 | style="color:#000;" | <div id="mp-tfa" style="padding:2px 5px">

@@ Line 28: / Line 28: @@
 * [[Special_Sessions#ss2| SS2 Kalman Filters in Nonlinear State Estimation]]
 * [[Special_Sessions#ss3| SS3 Data Fusion Methods for Indoor Localization of People and Objects]]
-* [[Special_Sessions#ss4| SS4 Multimodal Image Processing and Fusion ]]
+* [[Special_Sessions#ss4| SS4 Multimodal Image Processing and Fusion]]
-* [[Special_Sessions#ss5| SS5 Homotopy Methods in State Estimation ]]
+* [[Special_Sessions#ss5| SS5 Homotopy Methods in State Estimation]]
 </div>
 |}
@@ Line 114: / Line 115: @@
 | class="MainPageBG" style="width:100%; border:1px solid #bdd6c6; background:#e7f7e7; vertical-align:top; color:#000;" |
 {| id="mp-left" style="width:100%; vertical-align:top; background:#e7f7e76;"
-| style="padding:2px;" | <h2 id="mp-tfa-h2" style="margin:3px; background:#d6efd6; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #bdd6c6; text-align:left; color:#000; padding:0.2em 0.4em;">SS4 Multimodal Image Processing and Fusion </h2>
+| style="padding:2px;" | <h2 id="mp-tfa-h2" style="margin:3px; background:#d6efd6; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #bdd6c6; text-align:left; color:#000; padding:0.2em 0.4em;">SS4 Multimodal Image Processing and Fusion</h2>
 |-
 | style="color:#000;" | <div id="mp-tfa" style="padding:2px 5px">
@@ Line 132: / Line 133: @@
 | class="MainPageBG" style="width:100%; border:1px solid #f2ea7e; background:#ffffe8; vertical-align:top; color:#000;" |
 {| id="mp-left" style="width:100%; vertical-align:top; background:#ffffe8;"
-| style="padding:2px;" | <h2 id="mp-tfa-h2" style="margin:3px; background:#fff7bd; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #f2ea7e; text-align:left; color:#000; padding:0.2em 0.4em;">SS5 Homotopy Methods in State Estimation </h2>
+| style="padding:2px;" | <h2 id="mp-tfa-h2" style="margin:3px; background:#fff7bd; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #f2ea7e; text-align:left; color:#000; padding:0.2em 0.4em;">SS5 Homotopy Methods in State Estimation</h2>
 |-
 | style="color:#000;" | <div id="mp-tfa" style="padding:2px 5px">
@@ Line 140: / Line 141: @@
 '''Organizers:''' [mailto:martin.pander@kit.edu Martin Pander], [mailto:uwe.hanebeck@kit.edu Uwe D. Hanebeck]
 |-

@@ Line 44: / Line 44: @@
 |-
 | style="color:#000;" | <div id="mp-tfa" style="padding:2px 5px">
-'''Description:'''
+'''Description:''' Automotive transportation is currently evolving at an unprecedented rate. Future vehicles operating in a highly assisted and autonomous mode will need the ability to function on any road possible, in a safe, legal and socially acceptable manner and without access to high-precision, precompiled maps. Therefore, at the heart of any autonomous functionality will be the ability of a vehicle to sense its environment, produce a map of static objects in the environment and to track both itself and other dynamic targets within that environment. For autonomous vehicles to be commercially viable it must achieve this high level of situational awareness using only commercially viable sensors. Multi-sensor data fusion offers the ability to greatly reduce the uncertainty of state estimates and estimate physical states which might otherwise be unobservable.
-'''Organizers:''' [mailto:d.s.clarke@cranfield.ac.uk Daniel Clarke], [mailto:michael.fiegert@siemens.com Michael Fiegert], [mailto:zhang@fortiss.org Feihu Zhang], [mailto:gulati@fortiss.org Dhiraj Gulati], [mailto:benjamin.noack@kit.edu Benjamin Noack], [mailto:florian.faion@kit.edu Florian Faion],
+In addition to the challenge of fusing sensors organic to the vehicle, many future infrastructure projects envisage the concept where vehicles will be connected with each other and with sensors in the infrastructure to further improve situational awareness. This presents many challenges where there may be poorly understood correlation, or poor trust in externally shared information, along with constraints in terms of bandwidth and computational capacity. Furthermore, there exist both challenges and opportunities for understanding and characterising the interaction between the driver and the vehicle.
 </div>

← Older revision		Revision as of 09:37, 17 May 2016
Line 14:		Line 14:
	\| style="border:1px solid transparent;" \|<br />		\| style="border:1px solid transparent;" \|<br />
	\|-		\|-
		+
		+	<!-- List of Special Sessions of MFI 2016 -->
		+	{\| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;"
		+	<!-- List of Special Sessions of MFI 2016 -->
		+	\| class="MainPageBG" style="width:100%; border:1px solid #f2ea7e; background:#ffffe8; vertical-align:top; color:#000;" \|
		+	{\| id="mp-left" style="width:100%; vertical-align:top; background:#ffffe8;"
		+	\| style="padding:2px;" \| <h2 id="mp-tfa-h2" style="margin:3px; background:#fff7bd; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #f2ea7e; text-align:left; color:#000; padding:0.2em 0.4em;">List of Special Sessions of MFI 2016</h2>
		+	\|-
		+	\| style="color:#000;" \| <div id="mp-tfa" style="padding:2px 5px">
		+	As additional special sessions are announced, the title of each confirmed special session will be added to the topic list above in the paper submission interface. Authors submitting to a special session need to delay their submission until the special sessions are available. <!--If the special session you wish to submit to is not available yet, consider delaying your submission until it becomes available. In case you find a new special session that appears to be a good match for your paper and would like your paper to be considered for presentation in that session, you can use the “Edit Submission” tool to add that session to the topics associated with your paper.-->
		+
		+	* [[Special_Sessions#ss1\| SS1 Multi-Sensor Data Fusion for Autonomous Vehicles]]
		+	* [[Special_Sessions#ss2\| SS2 Kalman Filters in Nonlinear State Estimation]]
		+	* [[Special_Sessions#ss3\| SS3 Data Fusion Methods for Indoor Localization of People and Objects]]
		+	* [[Special_Sessions#ss4\| SS4 Multimodal Image Processing and Fusion ]]
		+	* [[Special_Sessions#ss5\| SS5 Homotopy Methods in State Estimation ]]
		+	</div>
		+	\|}
		+	\| style="border:1px solid transparent;" \|<br />
		+	\|-
		+
		+	<!-- MFI 2016 Accepted Special Sessions -->
		+	{\| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;"
		+	<div id="ss1">
		+	<!-- SS1 Multi-Sensor Data Fusion for Autonomous Vehicles -->
		+	\| class="MainPageBG" style="width:100%; border:1px solid #d6bdde; background:#f7eff7; vertical-align:top; color:#000;" \|
		+	{\| id="mp-left" style="width:100%; vertical-align:top; background:#e7f7e76;"
		+	\| style="padding:2px;" \| <h2 id="mp-tfa-h2" style="margin:4px; background:#e7deef; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #d6bdde; text-align:left; color:#000; padding:0.2em 0.4em;">SS1 Multi-Sensor Data Fusion for Autonomous Vehicles</h2>
		+	\|-
		+	\| style="color:#000;" \| <div id="mp-tfa" style="padding:2px 5px">
		+	'''Description:'''
		+
		+	'''Organizers:''' [mailto:d.s.clarke@cranfield.ac.uk Daniel Clarke], [mailto:michael.fiegert@siemens.com Michael Fiegert], [mailto:zhang@fortiss.org Feihu Zhang], [mailto:gulati@fortiss.org Dhiraj Gulati], [mailto:benjamin.noack@kit.edu Benjamin Noack], [mailto:florian.faion@kit.edu Florian Faion],
		+
		+	</div>
		+	\|-
		+	\|}
		+	\| style="border:1px solid transparent;" \|<br />
		+	\|-
		+
		+	<!-- MFI 2016 Accepted Special Sessions -->
		+	{\| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;"
		+	<div id="ss2">
		+	<!-- SS2 Kalman Filters in Nonlinear State Estimation -->
		+	\| class="MainPageBG" style="width:100%; border:1px solid #f36766; background:#f9d6c9; vertical-align:top; color:#000;" \|
		+	{\| id="mp-left" style="width:100%; vertical-align:top; background:#f9d6c9;"
		+	\| style="padding:2px;" \| <h2 id="mp-tfa-h2" style="margin:3px; background:#f5baa3; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #f36766; text-align:left; color:#000; padding:0.2em 0.4em;">SS2 Kalman Filters in Nonlinear State Estimation</h2>
		+	\|-
		+	\| style="color:#000;" \| <div id="mp-tfa" style="padding:2px 5px">
		+	'''Description:''' Nonlinear state estimation is an important component in navigation, robotics, object tracking, and many other current research fields. Besides popular but computational expensive particle filters, variants of nonlinear Kalman filters or LMMSE estimators are widely used methods for state estimation. Such filters include for example the Unscented Kalman Filter, the Divided Difference Filter, or iterated Kalman filters. This session aims to cover the recent advances in the area of nonlinear Kalman filters with an emphasis on sampling and sigma-point set design, linearization techniques, and applications of Kalman filters in nonlinear state estimation scenarios.
		+
		+	'''Organizers:''' [mailto:jannik.steinbring@kit.edu Jannik Steinbring], [mailto:uwe.hanebeck@kit.edu Uwe D. Hanebeck]
		+	</div>
		+	\|-
		+	\|}
		+	\| style="border:1px solid transparent;" \|<br />
		+	\|-
		+
		+
		+	<!-- MFI 2016 Accepted Special Sessions -->
		+	{\| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;"
		+	<div id="ss3"></div>
		+	<!-- SS3 Data Fusion Methods for Indoor Localization of People and Objects -->
		+	\| class="MainPageBG" style="width:100%; border:1px solid #a3babf; background:#f5fdff; vertical-align:top; color:#000;" \|
		+	{\| id="mp-left" style="width:100%; vertical-align:top; background:#e7f7e76;"
		+	\| style="padding:2px;" \| <h2 id="mp-tfa-h2" style="margin:3px; background:#ceecf2; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #a3babf; text-align:left; color:#000; padding:0.2em 0.4em;">SS3 Data Fusion Methods for Indoor Localization of People and Objects</h2>
		+	\|-
		+	\| style="color:#000;" \| <div id="mp-tfa" style="padding:2px 5px">
		+	'''Description:''' Indoor positioning has gained great importance as technology allows for affordable
		+	realtime sensing and processing systems. Researchers and developers can take
		+	advantage of the pervasiveness of WSNs (e.g., in the form of WLAN) and mobile sensors
		+	(such as smartphones) to obtain more accurate results by exploiting already existing
		+	infrastructure. Applications for indoor positioning include pedestrian navigation in
		+	public buildings and shops, location based services, safety for the elderly and
		+	impaired, museum guides, surveillance tasks, and also tracking products in manufacturing,
		+	warehousing, etc. Unlike outdoor environments, which are covered by GNSS to a
		+	satisfying extent, indoor navigation faces additional challenges depending on the
		+	underlying measurement system such as occlusions, reflections and attenuation. While
		+	there are a great variety of sensors and measuring principles, in practice every single
		+	measuring technique suffers from deficits. While RF and (ultra-)sound are subject to
		+	multipath propagation, optical systems are intolerant to NLOS conditions. Some systems
		+	require setting up beacons, while others are self-calibrating and easy-to-install.
		+	Data fusion can overcome these limitations by combining complementary and redundant
		+	sensing techniques, with the application of algorithmic methods such as stochastic filtering.
		+
		+	'''Organizers:''' [mailto:antonio.zea@kit.edu Antonio Zea], [mailto:florian.faion@kit.edu Florian Faion], [mailto:uwe.hanebeck@kit.edu Uwe D. Hanebeck]
		+
		+	\|-
		+	\|}
		+	\| style="border:1px solid transparent;" \|<br />
		+	\|-
		+
		+	<!-- MFI 2016 Accepted Special Sessions -->
		+	{\| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;"
		+	<div id="ss4"></div>
		+	<!-- SS4 Multimodal Image Processing and Fusion -->
		+	\| class="MainPageBG" style="width:100%; border:1px solid #bdd6c6; background:#e7f7e7; vertical-align:top; color:#000;" \|
		+	{\| id="mp-left" style="width:100%; vertical-align:top; background:#e7f7e76;"
		+	\| style="padding:2px;" \| <h2 id="mp-tfa-h2" style="margin:3px; background:#d6efd6; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #bdd6c6; text-align:left; color:#000; padding:0.2em 0.4em;">SS4 Multimodal Image Processing and Fusion </h2>
		+	\|-
		+	\| style="color:#000;" \| <div id="mp-tfa" style="padding:2px 5px">
		+	'''Description:''' Since the launch of the first version of the Microsoft Kinect in 2010, setting up networks based on multimodal image sensors has become extremely popular. The novelty of these devices includes the availability of not only color information, but also infrared and depth information of a scene, at a price affordable to laymen. The combination of multiple sensors and image modalities has many advantages, such as simultaneous coverage of large environments, increased resolution, redundancy, multimodal scene information, and robustness against occlusion. However, in order to exploit these benefits, multiple challenges also need to be addressed: synchronization, calibration, registration, multi-sensor fusion, large amounts of data, and last but not least, sensor-specific stochastic and set-valued uncertainties. This Special Session addresses fundamental techniques, recent developments and future research directions in the field of multimodal image processing and fusion.
		+
		+	'''Organizers:''' [mailto:antonio.zea@kit.edu Antonio Zea], [mailto:florian.faion@kit.edu Florian Faion], [mailto:uwe.hanebeck@kit.edu Uwe D. Hanebeck]
		+
		+	\|-
		+	\|}
		+	\| style="border:1px solid transparent;" \|<br />
		+	\|-
		+
		+	<!-- MFI 2016 Accepted Special Sessions -->
		+	{\| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;"
		+	<div id="ss5"></div>
		+	<!-- SS5 Homotopy Methods in State Estimation -->
		+	\| class="MainPageBG" style="width:100%; border:1px solid #f2ea7e; background:#ffffe8; vertical-align:top; color:#000;" \|
		+	{\| id="mp-left" style="width:100%; vertical-align:top; background:#ffffe8;"
		+	\| style="padding:2px;" \| <h2 id="mp-tfa-h2" style="margin:3px; background:#fff7bd; font-family:inherit; font-size:120%; font-weight:bold; border:1px solid #f2ea7e; text-align:left; color:#000; padding:0.2em 0.4em;">SS5 Homotopy Methods in State Estimation </h2>
		+	\|-
		+	\| style="color:#000;" \| <div id="mp-tfa" style="padding:2px 5px">
		+	'''Description:''' In Bayesian state estimation, the inherent uncertainties of the underlying system and measurements are represented as probability density functions. Given new measurements, the predicted system state is updated to incorporate the new information. Traditionally, this information is introduced directly, which can lead to problems in recursive applications. In the case of discrete particle representations of the densities for example, the problem of particle degeneration is well known and has to be corrected for. Another approach is to gradually incorporate the new information through homotopy methods, allowing for a smooth transition of the underlying densities.
		+
		+	This special session is concerned with theoretical and practical aspects of homotopy methods in the context of state estimation and all works pertaining to fundamental techniques, recent developments and future research directions in this field are invited.
		+
		+	'''Organizers:''' [mailto:martin.pander@kit.edu Martin Pander], [mailto:uwe.hanebeck@kit.edu Uwe D. Hanebeck]
		+
		+	\|-
		+	\|}
		+	\| style="border:1px solid transparent;" \|<br />
		+	\|-
		+	__NOTOC____NOEDITSECTION__

@@ Line 1: / Line 1: @@
 <!--        CALL FOR SPECIAL SESSIONS        -->
-{| id="mp-upper" style="width: 80%; margin:4px 0 0 0; background:none; border-spacing: 0px;"
+{| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;"
 <div id="top">
 <!--        CFP Download        -->