As one of the research directions at OLIVES Lab @ Georgia Tech, we focus on the robustness of data-driven algorithms under diverse challenging conditions where trained models can possibly be depolyed. To achieve this goal, we introduced a large-sacle (~1.72M frames) traffic sign detection video dataset (CURE-TSD) which is among the most comprehensive datasets with controlled synthetic challenging conditions. The video sequences in the
The name format of the video files are as follows: “sequenceType_sequenceNumber_challengeSourceType_challengeType_challengeLevel.mp4”
· sequenceType: 01 – Real data 02 – Unreal data
· sequenceNumber: A number in between [01 – 49]
· challengeSourceType: 00 – No challenge source (which means no challenge) 01 – After affect
· challengeType: 00 – No challenge 01 – Decolorization 02 – Lens blur 03 – Codec error 04 – Darkening 05 – Dirty lens 06 – Exposure 07 – Gaussian blur 08 – Noise 09 – Rain 10 – Shadow 11 – Snow 12 – Haze
· challengeLevel: A number in between [01-05] where 01 is the least severe and 05 is the most severe challenge.
Test Sequences
We split the video sequences into 70% training set and 30% test set. The sequence numbers corresponding to test set are given below:
[01_04_x_x_x, 01_05_x_x_x, 01_06_x_x_x, 01_07_x_x_x, 01_08_x_x_x, 01_18_x_x_x, 01_19_x_x_x, 01_21_x_x_x, 01_24_x_x_x, 01_26_x_x_x, 01_31_x_x_x, 01_38_x_x_x, 01_39_x_x_x, 01_41_x_x_x, 01_47_x_x_x, 02_02_x_x_x, 02_04_x_x_x, 02_06_x_x_x, 02_09_x_x_x, 02_12_x_x_x, 02_13_x_x_x, 02_16_x_x_x, 02_17_x_x_x, 02_18_x_x_x, 02_20_x_x_x, 02_22_x_x_x, 02_28_x_x_x, 02_31_x_x_x, 02_32_x_x_x, 02_36_x_x_x]
The videos with all other sequence numbers are in the training set. Note that “x” above refers to the variations listed earlier.
The name format of the annotation files are as follows: “sequenceType_sequenceNumber.txt“
Challenge source type, challenge type, and challenge level do not affect the annotations. Therefore, the video sequences that start with the same sequence type and the sequence number have the same annotations.
· sequenceType: 01 – Real data 02 – Unreal data
· sequenceNumber: A number in between [01 – 49]
The format of each line in the annotation file (txt) should be: “frameNumber_signType_llx_lly_lrx_lry_ulx_uly_urx_ury”. You can see a visual coordinate system example in our GitHub page.
· frameNumber: A number in between [001-300]
· signType: 01 – speed_limit 02 – goods_vehicles 03 – no_overtaking 04 – no_stopping 05 – no_parking 06 – stop 07 – bicycle 08 – hump 09 – no_left 10 – no_right 11 – priority_to 12 – no_entry 13 – yield 14 – parking
- Categories:
As one of the research directions at OLIVES Lab @ Georgia Tech, we focus on the robustness of data-driven algorithms under diverse challenging conditions where trained models can possibly be depolyed.
The name format of the provided images are as follows: "sequenceType_signType_challengeType_challengeLevel_Index.bmp"
-
sequenceType: 01 - Real data 02 - Unreal data
-
signType: 01 - speed_limit 02 - goods_vehicles 03 - no_overtaking 04 - no_stopping 05 - no_parking 06 - stop 07 - bicycle 08 - hump 09 - no_left 10 - no_right 11 - priority_to 12 - no_entry 13 - yield 14 - parking
-
challengeType: 00 - No challenge 01 - Decolorization 02 - Lens blur 03 - Codec error 04 - Darkening 05 - Dirty lens 06 - Exposure 07 - Gaussian blur 08 - Noise 09 - Rain 10 - Shadow 11 - Snow 12 - Haze
-
challengeLevel: A number in between [01-05] where 01 is the least severe and 05 is the most severe challenge.
-
Index: A number shows different instances of traffic signs in the same conditions.
- Categories:
The files in this dataset each contain vectors Time, PEDAL, SPEED, ACCEL, VOLTAGE and CURRENT related to an Electric Vehicle travelling on one of four different roads, mostly in urban areas. Data is obtained from the CAN bus of the vehicle (a Zhidou ZD model ZD2) resampled in order to obtain a single time coordinate and stored in the dataset.
- Categories:
This dataset is in support of my planned research paper shortly to be submitted to "IEEE Transactions on Power Electronics".
The results contained in this dataset are graphs which give intutive idea on the control characteristics, whether the pole/zero is on the imaginary axis or the right half plane. The switching frequency for these controllers is generally 20 kHz or more.
In this dataset, switching frequency has been increased from 20 kHz to 1MHZ , at 26 different PWM frequencies and the comparison of the resulting characteristics are drawn.
- Categories:
Vision and lidar are complementary sensors that are incorporated into many applications of intelligent transportation systems. These sensors have been used to great effect in research related to perception, navigation and deep-learning applications. Despite this success, the validation of algorithm robustness has recently been recognised as a major challenge for the massive deployment of these new technologies. It is well known that algorithms and models trained or tested with a particular dataset tend not to generalise well for other scenarios.
For detailed information about this dataset and the tools, please go to our website: http://its.acfr.usyd.edu.au/datasets/usyd-campus-dataset/
- Categories:

Normal
0
false
false
false
EN-US
X-NONE
AR-SA
These tables are presented more details of the proposed methodologies. These tables include problem, methodology, type, data from autonomous vehicle, base case, result, evaluation method, and evolutionary characteristics. The proposed methodologies are categorized by considering the goal.
- Categories:
The odometric model is simulated herein. We described the trajectory of such one odometric model, with the delta of the heading angle given as one parameter of the simulation. The iterations show that the trajectory is well in the continuity of the variations of the heading angle. Moreover the distance in X and in Y are shown for the vehicle to be driven in the trajectory of the odometric model.
Please take the odometric model in the context.
- Categories:

The rawdata.csv profile indicates the traffic analysis based mobility patterns. we extract human trips from Call Records Detail data. Combining traffic analysis zone dataset, we map each trip record to the zones with the same origin zones and destination zones. After this, we can obtain this dataset. This dataset stores the hourly number of departure and arrival trips in each traffic analysis zone.
The POI-importance.csv profile indicates the term frequency-inverse doument frequency(TF-IDF) of each category of poi the in each traffic analysis zone.
- Categories:

This dataset used in the experiment of paper "Bus Ridesharing Scheduling Problem". This is a real-world bus ridesharing scheduling problem of Chengdu city in China, which includes 10 depots, 2,000 trips.
- Categories:

This is the dataset used in the experiment of paper "Bus Pooling: A Large-Scale Bus Ridesharing Service". The dataset contains 60,822,634 trajectory data from 11,922 Shanghai taxis from one day (Apr 1, 2018). The 100 groups of coordinate sets containing three coordinates as experimental samples are used to compare the effectiveness and efficiency of location-allocation algorithms.
- Categories: