Object detections are critical technologies for the safety of pedestrians and drivers in autonomous vehicles. Above all, occluded pedestrian detection is still a challenging topic. We propose a new detection scheme for occluded pedestrian detection by means of lidar–radar sensor fusion. In the proposed method, the lidar and radar regions of interest (RoIs) have been selected based on the respective sensor measurement. Occluded depth is a new means to determine whether an occluded target exists or not. The occluded depth is a region projected out by expanding the longitudinal distance with maintaining the angle formed by the outermost two end points of the lidar RoI. The occlusion RoI is the overlapped region made by superimposing the radar RoI and the occluded depth. The object within the occlusion RoI is detected by the radar measurement information and the occluded object is estimated as a pedestrian based on human Doppler distribution. Additionally, various experiments are performed in detecting a partially occluded pedestrian in outdoor as well as indoor environments. According to experimental results, the proposed sensor fusion scheme has much better detection performance compared to the case without our proposed method.
A metamaterials (MTM)-core slab waveguide overlaid with a MTM buffer layer was used to enhance an evanescent field. The guided modes were graphically obtained by a new dispersion equation of the four-layered MTM-core slab waveguide modeled to have four layers, including an air layer, buffer layer, slab waveguide layer, and substrate layer. With the tuning of the refractive index and width of the MTM-buffer layer, abuffer layer with one-tenth of the core-layer width was obtained together with the refractive index of 1.7, making the evanescent field increase up to 1.8 times.
Today, 77 GHz FMCW (Frequency Modulation Continuous Wave) radar has strong advantages of range and velocity
detection for automotive applications. However, FMCW radar brings out ghost targets and missed targets in multi-target
situations. In this paper, in order to resolve these limitations, we propose an effective pairing algorithm, which consists
of two steps. In the proposed method, a waveform with different slopes in two periods is used. In the 1st pairing
processing, all combinations of range and velocity are obtained in each of two wave periods. In the 2nd pairing step,
using the results of the 1st pairing processing, fine range and velocity are detected. In that case, we propose the range-velocity
windowing technique in order to compensate for the non-ideal beat-frequency characteristic that arises due to
the non-linearity of the RF module. Based on experimental results, the performance of the proposed algorithm is
improved compared with that of the typical method.
To measure a level of a flammable liquid, optical sensing methods have been reported more effective than other methods
based on mechanical and electrical methods. This paper reports a new method that uses a collimator and a pipe to
measure the liquid level. The presented liquid-level sensor consists of a gradient-index lens (GRIN lens), a metal pipe
with small holes, and a floating buoy as a mirror. The liquid in the tank flows into the pipe through small holes and the
floating buoy coated with aluminum will float over the liquid. The light collimated by a GRIN lens will be reflected at
the floating buoy, which operates like mirror. The light reflected from the mirror is refocused through the GRIN lens and
is varied as a function of the liquid distance. It is a simple design using a pipe to collect easily the. The experimental
result was obtained using a pipe with the height of 2 m and width of 10 mm. The power loss was decreased with the ratio
of 30 dB/m. This low-cost configuration easily collects the reflected light from the liquid surface without complicated
aligning.
In this paper, we present a multi-vehicle tracking method that uses integrated position and motion tracking methods to minimize missing and false detection. No existing state-of-the-art vehicle detection method can detect all the vehicles on the road and remove all false positive alarms. Therefore, a robust tracking-by-detection algorithm is necessary to minimize the number of false positive and false negative alarms. In multi-vehicle tracking, there are three types of errors such as false negative alarms, false positive alarms, and track identity switches. False negative and false positive alarms are caused by an imperfect detection algorithm, while track identity switches are caused by measurement-to-track pair confusion. Our tracking-by-detection method minimizes these errors while processing in real-time for online application. Sparse false positive alarms are reduced by a track initialization procedure. Motion tracking with selected features can minimize false negative alarms. A data association algorithm with complementary global and local distance prevents tracks from connecting measurements incorrectly. The proposed method was evaluated and verified in challenging, real road environments. The experimental results demonstrate that our multi-vehicle tracking method remarkably reduces false positive and false negative alarms and performs better than previous methods.
To improve road safety and realize intelligent transportation, Ultra-Wideband (UWB) radars sensor in the 24 GHz
domain are currently under development for many automotive applications. Automotive UWB radar sensor must be
small, require low power and inexpensive. By employing a direct conversion receiver, automotive UWB radar sensor is
able to meet size and cost reduction requirements. We developed Automotive UWB radar sensor for automotive
applications. The developed receiver of the automotive radar sensor is direct conversion architecture. Direct conversion
architecture poses a dc-offset problem. In automotive UWB radar, Doppler frequency is used to extract velocity. The
Doppler frequency of a vehicle can be detected using zero-padding Fast Fourier Transform (FFT). However, a zero-padding
FFT error is occurs due to DC-offset problem in automotive UWB radar sensor using a direct conversion
receiver. Therefore, dc-offset problem corrupts velocity ambiguity. In this paper we proposed a mean-padding method to
reduce zero-padding FFT error due to DC-offset in automotive UWB radar using direct conversion receiver, and verify
our proposed method with computer simulation and experiment using developed automotive UWB radar sensor. We
present the simulation results and experiment result to compare velocity measurement probability of the zero-padding
FFT and the mean-padding FFT. The proposed algorithm simulated using Matlab and experimented using designed the
automotive UWB radar sensor in a real road environment. The proposed method improved velocity measurement
probability.
In this paper, we design and implement a digital impulse generator using a DCM block and an OSERDES block for a
24GHz UWB impulse-Doppler radar. The Federal Communications Commission (FCC) has confirmed the spectrum
from 22 to 29GHz for UWB radar with a limit power of -41.3dBm/MHz. UWB signal possesses an absolute bandwidth
larger than 500MHz or a relative bandwidth up to 20%. The vehicle radar is the key technology with the inherent
advantage detected the distance and the velocity regardless of weather. Radar has a role to measure the distance and the
velocity of long-distance vehicle. But, the radar with 1m resolution is difficult to satisfy the detection performance in the
blind spot zone because the blind spot zone needs high resolution. So, UWB impulse-Doppler radar with 30cm
resolution is suitable for the blind spot zone. The designed impulse generator has a 2ns pulse width and 100us PRI. We
perform simulations through Xilinx ISE; experiments use a spectrum analyzer and a digital oscilloscope. For UWB
radar, we use an AD9779 DAC module with a 1Gsps maximum sampling rate. For equipment, we use a TDS5104B
oscilloscope of Tektronix with 3dB bandwidth at 1GHz for the analysis of the time domain and an E4448A spectrum
analyzer of Agilent with a 50GHz spectrum for the analysis of the frequency domain. The results of the digital impulse
measurement show a 2ns pulse width in the time domain, a 500MHz bandwidth, and a 10KHz spectrum peak in the
frequency domain.
This paper presents stereo vision-based vehicle detection approach on the road using a road feature and disparity histogram. It is not easy to detect only vehicles robustly on the road in various traffic situations, for example, a nonflat road or a multiple-obstacle situation. This paper focuses on the improvement of vehicle detection performance in various real traffic situations. The approach consists of three steps, namely obstacle localization, obstacle segmentation, and vehicle verification. First, we extract a road feature from v-disparity maps binarized using the most frequent values in each row and column, and adopt the extracted road feature as an obstacle criterion in column detection. However, many obstacles still coexist in each localized obstacle area. Thus, we divide the localized obstacle area into multiple obstacles using a disparity histogram and remerge the divided obstacles using four criteria parameters, namely the obstacle size, distance, and angle between the divided obstacles, and the difference of disparity values. Finally, we verify the vehicles using a depth map and gray image to improve the performance. We verify the performance of our proposed method by conducting experiments in various real traffic situations. The average recall rate of vehicle detection is 95.5%.
In this paper, we present a visual obstacle detection and tracking system based on a dense stereo vision method. We
combine a global stereo matcher with a correlation based cost function for generating a reliable disparity-map. An NCC
algorithm is robust to illumination variation, and a BP based global disparity computation algorithm is efficient for
recovering the disparity information of a large textureless area in real driving scenes. Then an obstacle detector and a
tracker module are implemented and tested under actual driving conditions. Using U-V disparity representation, a road
profile is efficiently extracted, and obstacle ROI can be detected. In the process of obstacle detection, a few heuristic
constraints are applied to exclude wrong candidates, and a further verification step is proceeded by a tracker.
Implemented system offers accurate and reliable range images under various noisy imaging conditions, which results in
robust detection and tracking performance.
In this paper, we present a low memory-cost message iteration architecture for a fast belief propagation(BP) algorithm.
To meet the real-time goal, our architecture basically follows multi-scale BP method and truncated linear smoothness
cost model. We observe that the message iteration process in BP requires a huge intermediate buffer to store four
directional messages of the whole node. Therefore, instead of updating all the node messages in each iteration sequence,
we propose that individual node could be completed iteration process in ahead and consecutively execute it node by
node. The key ideas in this paper focus on both maximizing architecture's parallelism and minimizing implementation
cost overhead. Therefore, we first apply a pipelined architecture to each iteration stage that is executed independently.
Note that pipelining makes it faster message throughput at a single iteration cycle rather than consuming whole iteration
cycle time as previously. We also make multiple message update nodes as a minimal processing unit to maximize the
parallelism. For the multi-scale BP method, the proposed parallel architecture does not cause additional execution time
for processing the nodes in the down-scaled Markov Random Field(MRF). Considering VGA image size, 4 iterations per
each scale and 64 disparity levels, our approach can reduce memory complexity by 99.7% and make it 340 times faster
than the general multi-scale BP architecture.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.