Trends in Vehicle Re-Identification Past, Present, and Future: A Comprehensive Review

Vehicle Re-identification (re-id) over surveillance camera network with non-overlapping field of view is an exciting and challenging task in intelligent transportation systems (ITS). Due to its versatile applicability in metropolitan cities, it gained significant attention. Vehicle re-id matches targeted vehicle over non-overlapping views in multiple camera network. However, it becomes more difficult due to inter-class similarity, intra-class variability, viewpoint changes, and spatio-temporal uncertainty. In order to draw a detailed picture of vehicle re-id research, this paper gives a comprehensive description of the various vehicle re-id technologies, applicability, datasets, and a brief comparison of different methodologies. Our paper specifically focuses on vision-based vehicle re-id approaches, including vehicle appearance, license plate, and spatio-temporal characteristics. In addition, we explore the main challenges as well as a variety of applications in different domains. Lastly, a detailed comparison of current state-of-the-art methods performances over VeRi-776 and VehicleID datasets is summarized with future directions. We aim to facilitate future research by reviewing the work being done on vehicle re-id till to date.

Sub-Frame Evaluation of Frame Synchronization for Camera Network Using Linearly Oscillating Light Spot

Precisely evaluating the frame synchronization of the camera network is often required for accurate data fusion from multiple visual information. This paper presents a novel method to estimate the synchronization accuracy by using inherent visual information of linearly oscillating light spot captured in the camera images instead of using luminescence information or depending on external measurement instrument. The suggested method is compared to the conventional evaluation method to prove the feasibility. Our experiment result implies that the estimation accuracy of the frame synchronization can be achieved in sub-millisecond order.

LiCaNet: Further Enhancement of Joint Perception and Motion Prediction based on Multi-Modal Fusion

<p>The safety and reliability of autonomous driving pivots on the accuracy of perception and motion prediction pipelines, which in turn reckons primarily on the sensors deployed onboard. Slight confusion in perception and motion prediction can result in catastrophic consequences due to misinterpretation in later pipelines. Therefore, researchers have recently devoted considerable effort towards developing accurate perception and motion prediction models. To that end, we propose LIDAR Camera network (LiCaNet) that leverages multi-modal fusion to further enhance the joint perception and motion prediction performance accomplished in our earlier work. LiCaNet expands on our previous fusion network by adding a camera image to the fusion of RV image with historical BEV data sourced from a LIDAR sensor. We present a comprehensive evaluation to validate the outstanding performance of LiCaNet compared to the state-of-the-art. Experiments reveal that utilizing a camera sensor results in a substantial perception gain over our previous fusion network and a steep reduction in displacement errors. Moreover, the majority of the achieved improvement falls within camera range, with the highest registered for small and distant objects, confirming the significance of incorporating a camera sensor into a fusion network.</p>

LiCaNet: Further Enhancement of Joint Perception and Motion Prediction based on Multi-Modal Fusion

<p>The safety and reliability of autonomous driving pivots on the accuracy of perception and motion prediction pipelines, which in turn reckons primarily on the sensors deployed onboard. Slight confusion in perception and motion prediction can result in catastrophic consequences due to misinterpretation in later pipelines. Therefore, researchers have recently devoted considerable effort towards developing accurate perception and motion prediction models. To that end, we propose LIDAR Camera network (LiCaNet) that leverages multi-modal fusion to further enhance the joint perception and motion prediction performance accomplished in our earlier work. LiCaNet expands on our previous fusion network by adding a camera image to the fusion of RV image with historical BEV data sourced from a LIDAR sensor. We present a comprehensive evaluation to validate the outstanding performance of LiCaNet compared to the state-of-the-art. Experiments reveal that utilizing a camera sensor results in a substantial perception gain over our previous fusion network and a steep reduction in displacement errors. Moreover, the majority of the achieved improvement falls within camera range, with the highest registered for small and distant objects, confirming the significance of incorporating a camera sensor into a fusion network.</p>

The Australian Desert Fireball Network: overview and recent results

&lt;p&gt;The Desert Fireball Network is a fireball observing network which stretches across the southern part of the Australian continent. To date, it has over 50 cameras, covering an area of approximately 2.5m km2. Its purpose is to observe and triangulate fireballs, calculate trajectories for incoming meteorites. The camera network has been operational in digital form since 2012, and to date as captured approximately 1.5PTB of data, primarily all sky images. We present an overview of the DFN results to date, detailing the dataset of approximately 1500 orbits, and over 30 possible candidate meteorite falls, and describe the most recent results. In particular, the team have recently recovered two candidate meteorites; one from the Nullarbor and one from the Simpson Desert in South Australia. The comparison the stories of these recoveries illustrate the typical issues of searching meteorite searching, and of verifying the meteorite&amp;#8217;s provenance, and possible origin of the rocks is interesting to compare.&lt;/p&gt;

The Museum as a collector of vernacular born-digital photographs: a case study of the family camera network collection at the Royal Ontario Museum.

Active from April 2016 to March 2019, The Family Camera Network was a collaborative project that explored the relationship between family and photography. The project established a public archive at the Royal Ontario Museum (ROM) and The ArQuives. The collection is composed of photographs, albums, home videos and miscellaneous objects. Among the objects collected by the ROM are 126 born-digital photographs. This thesis focuses on the development of cataloguing methods for born-digital vernacular photographs using existing fields in the museum’s collection catalogue, TMS. Through the use of digital metadata, this thesis describes and analysis how information embedded in the born-digital archives can assist in the production of valuable collection records.